{"task":"Sentiment Analysis","dataset":"SST-2 Binary classification","metric_names":["Accuracy","Dev Accuracy","Attack Success Rate"],"rows":[{"id":43496,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"T5-11B","metrics":{"Accuracy":"97.5"},"paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","paper_date":"2019-10-23","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/t5"},{"title":"google-research/text-to-text-transfer-transformer","url":"https://github.com/google-research/text-to-text-transfer-transformer"},{"title":"amazon-science/chronos-forecasting","url":"https://github.com/amazon-science/chronos-forecasting"},{"title":"google-research/t5x","url":"https://github.com/google-research/t5x"},{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"thudm/swissarmytransformer","url":"https://github.com/thudm/swissarmytransformer"},{"title":"Ki6an/fastT5","url":"https://github.com/Ki6an/fastT5"},{"title":"google/seqio","url":"https://github.com/google/seqio"},{"title":"facebookresearch/atlas","url":"https://github.com/facebookresearch/atlas"},{"title":"conceptofmind/LaMDA-pytorch","url":"https://github.com/conceptofmind/LaMDA-pytorch"},{"title":"conceptofmind/lamda-rlhf-pytorch","url":"https://github.com/conceptofmind/lamda-rlhf-pytorch"},{"title":"thu-keg/omnievent","url":"https://github.com/thu-keg/omnievent"},{"title":"asahi417/lm-question-generation","url":"https://github.com/asahi417/lm-question-generation"},{"title":"abelriboulot/onnxt5","url":"https://github.com/abelriboulot/onnxt5"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"airc-keti/ke-t5","url":"https://github.com/airc-keti/ke-t5"},{"title":"yizhongw/tk-instruct","url":"https://github.com/yizhongw/tk-instruct"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"gulucaptain/dynamictrl","url":"https://github.com/gulucaptain/dynamictrl"},{"title":"google-research/t5x_retrieval","url":"https://github.com/google-research/t5x_retrieval"},{"title":"bigscience-workshop/architecture-objective","url":"https://github.com/bigscience-workshop/architecture-objective"},{"title":"dawn0815/UniSA","url":"https://github.com/dawn0815/UniSA"},{"title":"ibm/graph_ensemble_learning","url":"https://github.com/ibm/graph_ensemble_learning"},{"title":"wangcongcong123/ttt","url":"https://github.com/wangcongcong123/ttt"},{"title":"safakkbilici/Academic-Paper-Title-Recommendation","url":"https://github.com/safakkbilici/Academic-Paper-Title-Recommendation"},{"title":"bayer-science-for-a-better-life/data2text-bioleaflets","url":"https://github.com/bayer-science-for-a-better-life/data2text-bioleaflets"},{"title":"allenai/c4-documentation","url":"https://github.com/allenai/c4-documentation"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"lesterpjy/numeric-t5","url":"https://github.com/lesterpjy/numeric-t5"},{"title":"zhiqic/chartreader","url":"https://github.com/zhiqic/chartreader"},{"title":"LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer","url":"https://github.com/LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer"},{"title":"s-nlp/russe_detox_2022","url":"https://github.com/s-nlp/russe_detox_2022"},{"title":"skoltech-nlp/russe_detox_2022","url":"https://github.com/skoltech-nlp/russe_detox_2022"},{"title":"jongwooko/nash-pruning-official","url":"https://github.com/jongwooko/nash-pruning-official"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/t5"},{"title":"luomancs/retriever_reader_for_okvqa","url":"https://github.com/luomancs/retriever_reader_for_okvqa"},{"title":"qipengguo/p2_webnlg2020","url":"https://github.com/qipengguo/p2_webnlg2020"},{"title":"JunnYu/x-transformers-paddle","url":"https://github.com/JunnYu/x-transformers-paddle"},{"title":"Sharif-SLPL/t5-fa","url":"https://github.com/Sharif-SLPL/t5-fa"},{"title":"shivamraval98/multitask-t5_ae","url":"https://github.com/shivamraval98/multitask-t5_ae"},{"title":"junnyu/paddle_t5","url":"https://github.com/junnyu/paddle_t5"},{"title":"ChernovAndrey/chronos-forecasting-wasserstein","url":"https://github.com/ChernovAndrey/chronos-forecasting-wasserstein"},{"title":"cccntu/ft5-demo","url":"https://github.com/cccntu/ft5-demo"},{"title":"ArvinZhuang/BiTAG","url":"https://github.com/ArvinZhuang/BiTAG"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/t5"},{"title":"cccntu/ft5-demo-space","url":"https://github.com/cccntu/ft5-demo-space"},{"title":"xuetianci/pacit","url":"https://github.com/xuetianci/pacit"},{"title":"vgaraujov/seq2seq-spanish-plms","url":"https://github.com/vgaraujov/seq2seq-spanish-plms"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"thecodemasterk/Text-to-Text-transfer-transformers","url":"https://github.com/thecodemasterk/Text-to-Text-transfer-transformers"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/t5"},{"title":"KAGUYAHONGLAI/SRC","url":"https://github.com/KAGUYAHONGLAI/SRC"},{"title":"Nimesh-Patel/text-to-text-transfer-transformer","url":"https://github.com/Nimesh-Patel/text-to-text-transfer-transformer"},{"title":"souvikshanku/translit-former","url":"https://github.com/souvikshanku/translit-former"},{"title":"itzprashu1/prashant","url":"https://github.com/itzprashu1/prashant"},{"title":"2023-MindSpore-1/ms-code-164","url":"https://github.com/2023-MindSpore-1/ms-code-164"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43497,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"MT-DNN-SMART","metrics":{"Accuracy":"97.5"},"paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","paper_date":"2019-11-08","code_links":[{"title":"namisan/mt-dnn","url":"https://github.com/namisan/mt-dnn"},{"title":"microsoft/MT-DNN","url":"https://github.com/microsoft/MT-DNN"},{"title":"archinetai/smart-pytorch","url":"https://github.com/archinetai/smart-pytorch"},{"title":"archinetai/vat-pytorch","url":"https://github.com/archinetai/vat-pytorch"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"},{"title":"chunhuililili/mt_dnn","url":"https://github.com/chunhuililili/mt_dnn"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43498,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"T5-3B","metrics":{"Accuracy":"97.4"},"paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","paper_date":"2019-10-23","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/t5"},{"title":"google-research/text-to-text-transfer-transformer","url":"https://github.com/google-research/text-to-text-transfer-transformer"},{"title":"amazon-science/chronos-forecasting","url":"https://github.com/amazon-science/chronos-forecasting"},{"title":"google-research/t5x","url":"https://github.com/google-research/t5x"},{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"thudm/swissarmytransformer","url":"https://github.com/thudm/swissarmytransformer"},{"title":"Ki6an/fastT5","url":"https://github.com/Ki6an/fastT5"},{"title":"google/seqio","url":"https://github.com/google/seqio"},{"title":"facebookresearch/atlas","url":"https://github.com/facebookresearch/atlas"},{"title":"conceptofmind/LaMDA-pytorch","url":"https://github.com/conceptofmind/LaMDA-pytorch"},{"title":"conceptofmind/lamda-rlhf-pytorch","url":"https://github.com/conceptofmind/lamda-rlhf-pytorch"},{"title":"thu-keg/omnievent","url":"https://github.com/thu-keg/omnievent"},{"title":"asahi417/lm-question-generation","url":"https://github.com/asahi417/lm-question-generation"},{"title":"abelriboulot/onnxt5","url":"https://github.com/abelriboulot/onnxt5"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"airc-keti/ke-t5","url":"https://github.com/airc-keti/ke-t5"},{"title":"yizhongw/tk-instruct","url":"https://github.com/yizhongw/tk-instruct"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"gulucaptain/dynamictrl","url":"https://github.com/gulucaptain/dynamictrl"},{"title":"google-research/t5x_retrieval","url":"https://github.com/google-research/t5x_retrieval"},{"title":"bigscience-workshop/architecture-objective","url":"https://github.com/bigscience-workshop/architecture-objective"},{"title":"dawn0815/UniSA","url":"https://github.com/dawn0815/UniSA"},{"title":"ibm/graph_ensemble_learning","url":"https://github.com/ibm/graph_ensemble_learning"},{"title":"wangcongcong123/ttt","url":"https://github.com/wangcongcong123/ttt"},{"title":"safakkbilici/Academic-Paper-Title-Recommendation","url":"https://github.com/safakkbilici/Academic-Paper-Title-Recommendation"},{"title":"bayer-science-for-a-better-life/data2text-bioleaflets","url":"https://github.com/bayer-science-for-a-better-life/data2text-bioleaflets"},{"title":"allenai/c4-documentation","url":"https://github.com/allenai/c4-documentation"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"lesterpjy/numeric-t5","url":"https://github.com/lesterpjy/numeric-t5"},{"title":"zhiqic/chartreader","url":"https://github.com/zhiqic/chartreader"},{"title":"LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer","url":"https://github.com/LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer"},{"title":"s-nlp/russe_detox_2022","url":"https://github.com/s-nlp/russe_detox_2022"},{"title":"skoltech-nlp/russe_detox_2022","url":"https://github.com/skoltech-nlp/russe_detox_2022"},{"title":"jongwooko/nash-pruning-official","url":"https://github.com/jongwooko/nash-pruning-official"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/t5"},{"title":"luomancs/retriever_reader_for_okvqa","url":"https://github.com/luomancs/retriever_reader_for_okvqa"},{"title":"qipengguo/p2_webnlg2020","url":"https://github.com/qipengguo/p2_webnlg2020"},{"title":"JunnYu/x-transformers-paddle","url":"https://github.com/JunnYu/x-transformers-paddle"},{"title":"Sharif-SLPL/t5-fa","url":"https://github.com/Sharif-SLPL/t5-fa"},{"title":"shivamraval98/multitask-t5_ae","url":"https://github.com/shivamraval98/multitask-t5_ae"},{"title":"junnyu/paddle_t5","url":"https://github.com/junnyu/paddle_t5"},{"title":"ChernovAndrey/chronos-forecasting-wasserstein","url":"https://github.com/ChernovAndrey/chronos-forecasting-wasserstein"},{"title":"cccntu/ft5-demo","url":"https://github.com/cccntu/ft5-demo"},{"title":"ArvinZhuang/BiTAG","url":"https://github.com/ArvinZhuang/BiTAG"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/t5"},{"title":"cccntu/ft5-demo-space","url":"https://github.com/cccntu/ft5-demo-space"},{"title":"xuetianci/pacit","url":"https://github.com/xuetianci/pacit"},{"title":"vgaraujov/seq2seq-spanish-plms","url":"https://github.com/vgaraujov/seq2seq-spanish-plms"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"thecodemasterk/Text-to-Text-transfer-transformers","url":"https://github.com/thecodemasterk/Text-to-Text-transfer-transformers"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/t5"},{"title":"KAGUYAHONGLAI/SRC","url":"https://github.com/KAGUYAHONGLAI/SRC"},{"title":"Nimesh-Patel/text-to-text-transfer-transformer","url":"https://github.com/Nimesh-Patel/text-to-text-transfer-transformer"},{"title":"souvikshanku/translit-former","url":"https://github.com/souvikshanku/translit-former"},{"title":"itzprashu1/prashant","url":"https://github.com/itzprashu1/prashant"},{"title":"2023-MindSpore-1/ms-code-164","url":"https://github.com/2023-MindSpore-1/ms-code-164"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43499,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"MUPPET Roberta Large","metrics":{"Accuracy":"97.4"},"paper_url":"https://arxiv.org/abs/2101.11038v1","paper_title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","paper_date":"2021-01-26","code_links":[{"title":"facebook/muppet-roberta-base","url":"https://huggingface.co/facebook/muppet-roberta-base"},{"title":"facebook/muppet-roberta-large","url":"https://huggingface.co/facebook/muppet-roberta-large"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43500,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"ALBERT","metrics":{"Accuracy":"97.1"},"paper_url":"https://arxiv.org/abs/1909.11942v6","paper_title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","paper_date":"2019-09-26","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/nlp/albert"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/blob/develop/paddlenlp/transformers/albert/modeling.py"},{"title":"CLUEbenchmark/CLUE","url":"https://github.com/CLUEbenchmark/CLUE"},{"title":"brightmart/albert_zh","url":"https://github.com/brightmart/albert_zh"},{"title":"google-research/ALBERT","url":"https://github.com/google-research/ALBERT"},{"title":"Tencent/TurboTransformers","url":"https://github.com/Tencent/TurboTransformers"},{"title":"kpe/bert-for-tf2","url":"https://github.com/kpe/bert-for-tf2"},{"title":"lonePatient/albert_pytorch","url":"https://github.com/lonePatient/albert_pytorch"},{"title":"plkmo/BERT-Relation-Extraction","url":"https://github.com/plkmo/BERT-Relation-Extraction"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"lucidrains/routing-transformer","url":"https://github.com/lucidrains/routing-transformer"},{"title":"lucidrains/sinkhorn-transformer","url":"https://github.com/lucidrains/sinkhorn-transformer"},{"title":"graykode/ALBERT-Pytorch","url":"https://github.com/graykode/ALBERT-Pytorch"},{"title":"kamalkraj/ALBERT-TF2.0","url":"https://github.com/kamalkraj/ALBERT-TF2.0"},{"title":"lucidrains/compressive-transformer-pytorch","url":"https://github.com/lucidrains/compressive-transformer-pytorch"},{"title":"epfml/collaborative-attention","url":"https://github.com/epfml/collaborative-attention"},{"title":"Sanyuan-Chen/RecAdam","url":"https://github.com/Sanyuan-Chen/RecAdam"},{"title":"mindspore-lab/mindnlp","url":"https://github.com/mindspore-lab/mindnlp/blob/master/mindnlp/models/albert/albert.py"},{"title":"benywon/ReCO","url":"https://github.com/benywon/ReCO"},{"title":"KnightZhang625/BERT_TF","url":"https://github.com/KnightZhang625/BERT_TF"},{"title":"AdamStein97/Semi-Supervised-BERT-NER","url":"https://github.com/AdamStein97/Semi-Supervised-BERT-NER"},{"title":"mandubian/codenets","url":"https://github.com/mandubian/codenets"},{"title":"codegram/calbert","url":"https://github.com/codegram/calbert"},{"title":"yahah100/text_summarization","url":"https://github.com/yahah100/text_summarization"},{"title":"Soikonomou/albert_final_infer12","url":"https://github.com/Soikonomou/albert_final_infer12"},{"title":"xinyooo/ALBERT4Rec","url":"https://github.com/xinyooo/ALBERT4Rec"},{"title":"rajatgermany/qa-nlp","url":"https://github.com/rajatgermany/qa-nlp"},{"title":"Soikonomou/bert_new","url":"https://github.com/Soikonomou/bert_new"},{"title":"Soikonomou/bert_new_new","url":"https://github.com/Soikonomou/bert_new_new"},{"title":"Soikonomou/albert_final","url":"https://github.com/Soikonomou/albert_final"},{"title":"Soikonomou/albert_final_infer8","url":"https://github.com/Soikonomou/albert_final_infer8"},{"title":"benywon/Chinese-GPT-2","url":"https://github.com/benywon/Chinese-GPT-2"},{"title":"jpablou/Matching-The-Blanks-Ths","url":"https://github.com/jpablou/Matching-The-Blanks-Ths"},{"title":"vvvm23/albert","url":"https://github.com/vvvm23/albert"},{"title":"common-english/bert-all","url":"https://github.com/common-english/bert-all"},{"title":"AhmedYounes94/Semi-supervised-BERT-NER","url":"https://github.com/AhmedYounes94/Semi-supervised-BERT-NER"},{"title":"appcoreopc/berty","url":"https://github.com/appcoreopc/berty"},{"title":"lyqcom/albert","url":"https://github.com/lyqcom/albert"},{"title":"mtzcorporations/nlp_teamjodka","url":"https://github.com/mtzcorporations/nlp_teamjodka"},{"title":"cui0523/Code6","url":"https://github.com/cui0523/Code6/tree/main/albert"},{"title":"cypressd1999/FYP_2021","url":"https://github.com/cypressd1999/FYP_2021"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/albert"},{"title":"Mind23-2/MindCode-131","url":"https://github.com/Mind23-2/MindCode-131"},{"title":"2023-MindSpore-1/ms-code-219","url":"https://github.com/2023-MindSpore-1/ms-code-219/tree/main/albert"},{"title":"hieudepchai/BERT_IE","url":"https://github.com/hieudepchai/BERT_IE"},{"title":"DataScienceNigeria/ALBERT-for-Natural-Language-Processing","url":"https://github.com/DataScienceNigeria/ALBERT-for-Natural-Language-Processing"},{"title":"MindSpore-paper-code-3/code9","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/albert"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43501,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"StructBERTRoBERTa ensemble","metrics":{"Accuracy":"97.1"},"paper_url":"https://arxiv.org/abs/1908.04577v3","paper_title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","paper_date":"2019-08-13","code_links":[],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43502,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"XLNet (single model)","metrics":{"Accuracy":"97"},"paper_url":"https://arxiv.org/abs/1906.08237v2","paper_title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","paper_date":"2019-06-19","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/xlnet"},{"title":"zihangdai/xlnet","url":"https://github.com/zihangdai/xlnet"},{"title":"kaushaltrivedi/fast-bert","url":"https://github.com/kaushaltrivedi/fast-bert"},{"title":"utterworks/fast-bert","url":"https://github.com/utterworks/fast-bert"},{"title":"graykode/xlnet-Pytorch","url":"https://github.com/graykode/xlnet-Pytorch"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms/blob/master/bert4ms/models/xlnet.py"},{"title":"huggingface/xlnet","url":"https://github.com/huggingface/xlnet"},{"title":"cuhksz-nlp/SAPar","url":"https://github.com/cuhksz-nlp/SAPar"},{"title":"joshuaWang-bit/Textclassification-pytorch","url":"https://github.com/joshuaWang-bit/Textclassification-pytorch"},{"title":"fanchenyou/transformer-study","url":"https://github.com/fanchenyou/transformer-study"},{"title":"https-seyhan/BugAI","url":"https://github.com/https-seyhan/BugAI"},{"title":"NathanDuran/Sentence-Encoding-for-DA-Classification","url":"https://github.com/NathanDuran/Sentence-Encoding-for-DA-Classification"},{"title":"2miatran/Natural-Language-Processing","url":"https://github.com/2miatran/Natural-Language-Processing"},{"title":"chesterdu/contrastive_summary","url":"https://github.com/chesterdu/contrastive_summary"},{"title":"pauldevos/python-notes","url":"https://github.com/pauldevos/python-notes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/5/xlnet"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/xlnet"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/xlnet"},{"title":"samwisegamjeee/pytorch-transformers","url":"https://github.com/samwisegamjeee/pytorch-transformers"},{"title":"SambhawDrag/XLNet.jl","url":"https://github.com/SambhawDrag/XLNet.jl"},{"title":"tomgoter/nlp_finalproject","url":"https://github.com/tomgoter/nlp_finalproject"},{"title":"MS-P3/code7","url":"https://github.com/MS-P3/code7/tree/main/xlnet"},{"title":"zaradana/Fast_BERT","url":"https://github.com/zaradana/Fast_BERT"},{"title":"jonahwinninghoff/Text-Summarization","url":"https://github.com/jonahwinninghoff/Text-Summarization"},{"title":"listenviolet/XLNet","url":"https://github.com/listenviolet/XLNet"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43503,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"ELECTRA","metrics":{"Accuracy":"96.9"},"paper_url":"https://arxiv.org/abs/2003.10555v1","paper_title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","paper_date":"2020-03-23","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/blob/master/official/nlp/tasks/electra_task.py"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/electra"},{"title":"ThilinaRajapakse/simpletransformers","url":"https://github.com/ThilinaRajapakse/simpletransformers"},{"title":"google-research/electra","url":"https://github.com/google-research/electra"},{"title":"richarddwang/electra_pytorch","url":"https://github.com/richarddwang/electra_pytorch"},{"title":"lucidrains/electra-pytorch","url":"https://github.com/lucidrains/electra-pytorch"},{"title":"facebookresearch/multihop_dense_retrieval","url":"https://github.com/facebookresearch/multihop_dense_retrieval"},{"title":"okanvk/ENELPI---Soru-Cevap-Sistemi","url":"https://github.com/okanvk/ENELPI---Soru-Cevap-Sistemi"},{"title":"okanvk/Turkish-Reading-Comprehension-Question-Answering-Dataset","url":"https://github.com/okanvk/Turkish-Reading-Comprehension-Question-Answering-Dataset"},{"title":"rwbfd/OpenCompetitionV2","url":"https://github.com/rwbfd/OpenCompetitionV2"},{"title":"stefan-it/europeana-bert","url":"https://github.com/stefan-it/europeana-bert"},{"title":"MalteHB/-l-ctra","url":"https://github.com/MalteHB/-l-ctra"},{"title":"smallbenchnlp/ELECTRA-DeBERTa","url":"https://github.com/smallbenchnlp/ELECTRA-DeBERTa"},{"title":"gregdurrett/nlp-qa-finalproj","url":"https://github.com/gregdurrett/nlp-qa-finalproj"},{"title":"YChen1993/ELECRec","url":"https://github.com/YChen1993/ELECRec"},{"title":"jbeno/sentiment","url":"https://github.com/jbeno/sentiment"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/electra"},{"title":"bcaitech1/p2-klue-Heeseok-Jeong","url":"https://github.com/bcaitech1/p2-klue-Heeseok-Jeong"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43504,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"RoBERTa-large 355M + Entailment as Few-shot Learner","metrics":{"Accuracy":"96.9"},"paper_url":"https://arxiv.org/abs/2104.14690v1","paper_title":"Entailment as Few-Shot Learner","paper_date":"2021-04-29","code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/few_shot/efl"},{"title":"sunyilgdx/prompts4keras","url":"https://github.com/sunyilgdx/prompts4keras"},{"title":"cactilab/hateguard","url":"https://github.com/cactilab/hateguard"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43505,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"XLNet-Large (ensemble)","metrics":{"Accuracy":"96.8"},"paper_url":"https://arxiv.org/abs/1906.08237v2","paper_title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","paper_date":"2019-06-19","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/xlnet"},{"title":"zihangdai/xlnet","url":"https://github.com/zihangdai/xlnet"},{"title":"kaushaltrivedi/fast-bert","url":"https://github.com/kaushaltrivedi/fast-bert"},{"title":"utterworks/fast-bert","url":"https://github.com/utterworks/fast-bert"},{"title":"graykode/xlnet-Pytorch","url":"https://github.com/graykode/xlnet-Pytorch"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms/blob/master/bert4ms/models/xlnet.py"},{"title":"huggingface/xlnet","url":"https://github.com/huggingface/xlnet"},{"title":"cuhksz-nlp/SAPar","url":"https://github.com/cuhksz-nlp/SAPar"},{"title":"joshuaWang-bit/Textclassification-pytorch","url":"https://github.com/joshuaWang-bit/Textclassification-pytorch"},{"title":"fanchenyou/transformer-study","url":"https://github.com/fanchenyou/transformer-study"},{"title":"https-seyhan/BugAI","url":"https://github.com/https-seyhan/BugAI"},{"title":"NathanDuran/Sentence-Encoding-for-DA-Classification","url":"https://github.com/NathanDuran/Sentence-Encoding-for-DA-Classification"},{"title":"2miatran/Natural-Language-Processing","url":"https://github.com/2miatran/Natural-Language-Processing"},{"title":"chesterdu/contrastive_summary","url":"https://github.com/chesterdu/contrastive_summary"},{"title":"pauldevos/python-notes","url":"https://github.com/pauldevos/python-notes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/5/xlnet"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/xlnet"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/xlnet"},{"title":"samwisegamjeee/pytorch-transformers","url":"https://github.com/samwisegamjeee/pytorch-transformers"},{"title":"SambhawDrag/XLNet.jl","url":"https://github.com/SambhawDrag/XLNet.jl"},{"title":"tomgoter/nlp_finalproject","url":"https://github.com/tomgoter/nlp_finalproject"},{"title":"MS-P3/code7","url":"https://github.com/MS-P3/code7/tree/main/xlnet"},{"title":"zaradana/Fast_BERT","url":"https://github.com/zaradana/Fast_BERT"},{"title":"jonahwinninghoff/Text-Summarization","url":"https://github.com/jonahwinninghoff/Text-Summarization"},{"title":"listenviolet/XLNet","url":"https://github.com/listenviolet/XLNet"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43506,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"FLOATER-large","metrics":{"Accuracy":"96.7"},"paper_url":"https://arxiv.org/abs/2003.09229v1","paper_title":"Learning to Encode Position for Transformer with Continuous Dynamical Model","paper_date":"2020-03-13","code_links":[{"title":"xuanqing94/FLOATER","url":"https://github.com/xuanqing94/FLOATER"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43507,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"MUPPET Roberta base","metrics":{"Accuracy":"96.7"},"paper_url":"https://arxiv.org/abs/2101.11038v1","paper_title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","paper_date":"2021-01-26","code_links":[{"title":"facebook/muppet-roberta-base","url":"https://huggingface.co/facebook/muppet-roberta-base"},{"title":"facebook/muppet-roberta-large","url":"https://huggingface.co/facebook/muppet-roberta-large"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43508,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"RoBERTa (ensemble)","metrics":{"Accuracy":"96.7"},"paper_url":"https://arxiv.org/abs/1907.11692v1","paper_title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","paper_date":"2019-07-26","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/blob/develop/paddlenlp/transformers/roberta/modeling.py"},{"title":"salesforce/codet5","url":"https://github.com/salesforce/codet5"},{"title":"brightmart/roberta_zh","url":"https://github.com/brightmart/roberta_zh"},{"title":"utterworks/fast-bert","url":"https://github.com/utterworks/fast-bert"},{"title":"kaushaltrivedi/fast-bert","url":"https://github.com/kaushaltrivedi/fast-bert"},{"title":"Tencent/TurboTransformers","url":"https://github.com/Tencent/TurboTransformers"},{"title":"IndicoDataSolutions/finetune","url":"https://github.com/IndicoDataSolutions/finetune"},{"title":"xiaoqian19940510/text-classification-surveys","url":"https://github.com/xiaoqian19940510/text-classification-surveys"},{"title":"xiaoqian19940510/text-classification-","url":"https://github.com/xiaoqian19940510/text-classification-"},{"title":"oneflow-inc/libai","url":"https://github.com/oneflow-inc/libai"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"awslabs/mlm-scoring","url":"https://github.com/awslabs/mlm-scoring"},{"title":"hkuds/easyrec","url":"https://github.com/hkuds/easyrec"},{"title":"musixmatchresearch/umberto","url":"https://github.com/musixmatchresearch/umberto"},{"title":"octanove/shiba","url":"https://github.com/octanove/shiba"},{"title":"wzzzd/LM_NER","url":"https://github.com/wzzzd/LM_NER"},{"title":"sdadas/polish-roberta","url":"https://github.com/sdadas/polish-roberta"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms"},{"title":"few-shot-NER-benchmark/BaselineCode","url":"https://github.com/few-shot-NER-benchmark/BaselineCode"},{"title":"obi-ml-public/ehr_deidentification","url":"https://github.com/obi-ml-public/ehr_deidentification"},{"title":"GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data","url":"https://github.com/GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data"},{"title":"Karthik-Bhaskar/Context-Based-Question-Answering","url":"https://github.com/Karthik-Bhaskar/Context-Based-Question-Answering"},{"title":"benywon/ReCO","url":"https://github.com/benywon/ReCO"},{"title":"lashoun/hanna-benchmark-asg","url":"https://github.com/lashoun/hanna-benchmark-asg"},{"title":"dig-team/hanna-benchmark-asg","url":"https://github.com/dig-team/hanna-benchmark-asg"},{"title":"nguyenvulebinh/vietnamese-roberta","url":"https://github.com/nguyenvulebinh/vietnamese-roberta"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"aistairc/kirt_bert_on_abci","url":"https://github.com/aistairc/kirt_bert_on_abci"},{"title":"SindhuMadi/FakeNewsDetection","url":"https://github.com/SindhuMadi/FakeNewsDetection"},{"title":"traviscoan/cards","url":"https://github.com/traviscoan/cards"},{"title":"zfj1998/CodeBert-Code2Text","url":"https://github.com/zfj1998/CodeBert-Code2Text"},{"title":"haisongzhang/roberta-tiny-cased","url":"https://github.com/haisongzhang/roberta-tiny-cased"},{"title":"viethoang1512/kpa","url":"https://github.com/viethoang1512/kpa"},{"title":"devhemza/BERTweet_sentiment_analysis","url":"https://github.com/devhemza/BERTweet_sentiment_analysis"},{"title":"clovaai/textual-kd-slu","url":"https://github.com/clovaai/textual-kd-slu"},{"title":"znhy1024/protoco","url":"https://github.com/znhy1024/protoco"},{"title":"abdumaa/hiqualprop","url":"https://github.com/abdumaa/hiqualprop"},{"title":"simon-benigeri/narrative-generation","url":"https://github.com/simon-benigeri/narrative-generation"},{"title":"NathanDuran/Sentence-Encoding-for-DA-Classification","url":"https://github.com/NathanDuran/Sentence-Encoding-for-DA-Classification"},{"title":"blawok/named-entity-recognition","url":"https://github.com/blawok/named-entity-recognition"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/roberta"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/5/xlm_roberta"},{"title":"CalumPerrio/WNUT-2020","url":"https://github.com/CalumPerrio/WNUT-2020"},{"title":"duanchi1230/NLP_Project_AI2_Reasoning_Challenge","url":"https://github.com/duanchi1230/NLP_Project_AI2_Reasoning_Challenge"},{"title":"common-english/bert-all","url":"https://github.com/common-english/bert-all"},{"title":"ibm/vira-intent-discovery","url":"https://github.com/ibm/vira-intent-discovery"},{"title":"expertailab/spaceqa","url":"https://github.com/expertailab/spaceqa"},{"title":"abhishekanand1710/noiseandbias","url":"https://github.com/abhishekanand1710/noiseandbias"},{"title":"bfopengradient/NLP_ROBERTA","url":"https://github.com/bfopengradient/NLP_ROBERTA"},{"title":"tighu20/Kaggle-Tweet-Sentiment-Extraction","url":"https://github.com/tighu20/Kaggle-Tweet-Sentiment-Extraction"},{"title":"flexible-fl/flex-nlp","url":"https://github.com/flexible-fl/flex-nlp"},{"title":"bcaitech1/p2-klue-Heeseok-Jeong","url":"https://github.com/bcaitech1/p2-klue-Heeseok-Jeong"},{"title":"10Exahertz/Text-ResNet-on-Sentimental-LIAR-Fake-News","url":"https://github.com/10Exahertz/Text-ResNet-on-Sentimental-LIAR-Fake-News"},{"title":"knuddy/op_text","url":"https://github.com/knuddy/op_text"},{"title":"bluejurand/Kaggle_QA_Google_Labeling","url":"https://github.com/bluejurand/Kaggle_QA_Google_Labeling"},{"title":"2023-MindSpore-1/ms-code-163","url":"https://github.com/2023-MindSpore-1/ms-code-163"},{"title":"zaradana/Fast_BERT","url":"https://github.com/zaradana/Fast_BERT"},{"title":"mthcom/hscore-dataset-pruning","url":"https://github.com/mthcom/hscore-dataset-pruning"},{"title":"MS-P3/code7","url":"https://github.com/MS-P3/code7/tree/main/xlm_roberta_xl"},{"title":"pisalore/roberta_results","url":"https://github.com/pisalore/roberta_results"},{"title":"knuddj1/op_text","url":"https://github.com/knuddj1/op_text"},{"title":"ricaelum42/Contextual-Twitter-Sarcasm-Detection","url":"https://github.com/ricaelum42/Contextual-Twitter-Sarcasm-Detection"},{"title":"UnknownGenie/altered-BERT-KPE","url":"https://github.com/UnknownGenie/altered-BERT-KPE"},{"title":"G-4-R-Y/Tweet-Sentiment-Extraction-roBERTa-5fold","url":"https://github.com/G-4-R-Y/Tweet-Sentiment-Extraction-roBERTa-5fold"},{"title":"G-4-R-Y/Tweet-Sentiment-Extraction","url":"https://github.com/G-4-R-Y/Tweet-Sentiment-Extraction"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43509,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"DeBERTa (large)","metrics":{"Accuracy":"96.5"},"paper_url":"https://arxiv.org/abs/2006.03654v6","paper_title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","paper_date":"2020-06-05","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"microsoft/DeBERTa","url":"https://github.com/microsoft/DeBERTa"},{"title":"osu-nlp-group/mind2web","url":"https://github.com/osu-nlp-group/mind2web"},{"title":"neuralmind-ai/coliee","url":"https://github.com/neuralmind-ai/coliee"},{"title":"huberemanuel/DeBERTa","url":"https://github.com/huberemanuel/DeBERTa"},{"title":"Jason-J-Choi/DeBERTa_TxtClassifier","url":"https://github.com/Jason-J-Choi/DeBERTa_TxtClassifier"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/deberta"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/deberta"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/deberta_v2"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/deberta_v2"},{"title":"JONGWE1/Paddle-DeBERTa","url":"https://github.com/JONGWE1/Paddle-DeBERTa"},{"title":"Mind23-2/MindCode-161","url":"https://github.com/Mind23-2/MindCode-161"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/deberta"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/deberta_v2"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43510,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"MT-DNN-ensemble","metrics":{"Accuracy":"96.5"},"paper_url":"http://arxiv.org/abs/1904.09482v1","paper_title":"Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding","paper_date":"2019-04-20","code_links":[{"title":"namisan/mt-dnn","url":"https://github.com/namisan/mt-dnn"},{"title":"microsoft/MT-DNN","url":"https://github.com/microsoft/MT-DNN"},{"title":"chunhuililili/mt_dnn","url":"https://github.com/chunhuililili/mt_dnn"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43511,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"RoBERTa-large 355M (MLP quantized vector-wise, fine-tuned)","metrics":{"Accuracy":"96.4"},"paper_url":"https://arxiv.org/abs/2208.07339v2","paper_title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","paper_date":"2022-08-15","code_links":[{"title":"timdettmers/bitsandbytes","url":"https://github.com/timdettmers/bitsandbytes"},{"title":"huggingface/transformers-bloom-inference","url":"https://github.com/huggingface/transformers-bloom-inference"},{"title":"kohjingyu/fromage","url":"https://github.com/kohjingyu/fromage"},{"title":"alextmallen/adaptive-retrieval","url":"https://github.com/alextmallen/adaptive-retrieval"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43512,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"ASA + RoBERTa","metrics":{"Accuracy":"96.3"},"paper_url":"https://arxiv.org/abs/2206.12608v3","paper_title":"Adversarial Self-Attention for Language Understanding","paper_date":"2022-06-25","code_links":[{"title":"gingasan/adversarialsa","url":"https://github.com/gingasan/adversarialsa"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43513,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"T5-Large 770M","metrics":{"Accuracy":"96.3"},"paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","paper_date":"2019-10-23","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/t5"},{"title":"google-research/text-to-text-transfer-transformer","url":"https://github.com/google-research/text-to-text-transfer-transformer"},{"title":"amazon-science/chronos-forecasting","url":"https://github.com/amazon-science/chronos-forecasting"},{"title":"google-research/t5x","url":"https://github.com/google-research/t5x"},{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"thudm/swissarmytransformer","url":"https://github.com/thudm/swissarmytransformer"},{"title":"Ki6an/fastT5","url":"https://github.com/Ki6an/fastT5"},{"title":"google/seqio","url":"https://github.com/google/seqio"},{"title":"facebookresearch/atlas","url":"https://github.com/facebookresearch/atlas"},{"title":"conceptofmind/LaMDA-pytorch","url":"https://github.com/conceptofmind/LaMDA-pytorch"},{"title":"conceptofmind/lamda-rlhf-pytorch","url":"https://github.com/conceptofmind/lamda-rlhf-pytorch"},{"title":"thu-keg/omnievent","url":"https://github.com/thu-keg/omnievent"},{"title":"asahi417/lm-question-generation","url":"https://github.com/asahi417/lm-question-generation"},{"title":"abelriboulot/onnxt5","url":"https://github.com/abelriboulot/onnxt5"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"airc-keti/ke-t5","url":"https://github.com/airc-keti/ke-t5"},{"title":"yizhongw/tk-instruct","url":"https://github.com/yizhongw/tk-instruct"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"gulucaptain/dynamictrl","url":"https://github.com/gulucaptain/dynamictrl"},{"title":"google-research/t5x_retrieval","url":"https://github.com/google-research/t5x_retrieval"},{"title":"bigscience-workshop/architecture-objective","url":"https://github.com/bigscience-workshop/architecture-objective"},{"title":"dawn0815/UniSA","url":"https://github.com/dawn0815/UniSA"},{"title":"ibm/graph_ensemble_learning","url":"https://github.com/ibm/graph_ensemble_learning"},{"title":"wangcongcong123/ttt","url":"https://github.com/wangcongcong123/ttt"},{"title":"safakkbilici/Academic-Paper-Title-Recommendation","url":"https://github.com/safakkbilici/Academic-Paper-Title-Recommendation"},{"title":"bayer-science-for-a-better-life/data2text-bioleaflets","url":"https://github.com/bayer-science-for-a-better-life/data2text-bioleaflets"},{"title":"allenai/c4-documentation","url":"https://github.com/allenai/c4-documentation"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"lesterpjy/numeric-t5","url":"https://github.com/lesterpjy/numeric-t5"},{"title":"zhiqic/chartreader","url":"https://github.com/zhiqic/chartreader"},{"title":"LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer","url":"https://github.com/LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer"},{"title":"s-nlp/russe_detox_2022","url":"https://github.com/s-nlp/russe_detox_2022"},{"title":"skoltech-nlp/russe_detox_2022","url":"https://github.com/skoltech-nlp/russe_detox_2022"},{"title":"jongwooko/nash-pruning-official","url":"https://github.com/jongwooko/nash-pruning-official"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/t5"},{"title":"luomancs/retriever_reader_for_okvqa","url":"https://github.com/luomancs/retriever_reader_for_okvqa"},{"title":"qipengguo/p2_webnlg2020","url":"https://github.com/qipengguo/p2_webnlg2020"},{"title":"JunnYu/x-transformers-paddle","url":"https://github.com/JunnYu/x-transformers-paddle"},{"title":"Sharif-SLPL/t5-fa","url":"https://github.com/Sharif-SLPL/t5-fa"},{"title":"shivamraval98/multitask-t5_ae","url":"https://github.com/shivamraval98/multitask-t5_ae"},{"title":"junnyu/paddle_t5","url":"https://github.com/junnyu/paddle_t5"},{"title":"ChernovAndrey/chronos-forecasting-wasserstein","url":"https://github.com/ChernovAndrey/chronos-forecasting-wasserstein"},{"title":"cccntu/ft5-demo","url":"https://github.com/cccntu/ft5-demo"},{"title":"ArvinZhuang/BiTAG","url":"https://github.com/ArvinZhuang/BiTAG"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/t5"},{"title":"cccntu/ft5-demo-space","url":"https://github.com/cccntu/ft5-demo-space"},{"title":"xuetianci/pacit","url":"https://github.com/xuetianci/pacit"},{"title":"vgaraujov/seq2seq-spanish-plms","url":"https://github.com/vgaraujov/seq2seq-spanish-plms"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"thecodemasterk/Text-to-Text-transfer-transformers","url":"https://github.com/thecodemasterk/Text-to-Text-transfer-transformers"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/t5"},{"title":"KAGUYAHONGLAI/SRC","url":"https://github.com/KAGUYAHONGLAI/SRC"},{"title":"Nimesh-Patel/text-to-text-transfer-transformer","url":"https://github.com/Nimesh-Patel/text-to-text-transfer-transformer"},{"title":"souvikshanku/translit-former","url":"https://github.com/souvikshanku/translit-former"},{"title":"itzprashu1/prashant","url":"https://github.com/itzprashu1/prashant"},{"title":"2023-MindSpore-1/ms-code-164","url":"https://github.com/2023-MindSpore-1/ms-code-164"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43514,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Snorkel MeTaL(ensemble)","metrics":{"Accuracy":"96.2"},"paper_url":"http://arxiv.org/abs/1810.02840v2","paper_title":"Training Complex Models with Multi-Task Weak Supervision","paper_date":"2018-10-05","code_links":[{"title":"HazyResearch/metal","url":"https://github.com/HazyResearch/metal"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43515,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"PSQ (Chen et al., 2020)","metrics":{"Accuracy":"96.2"},"paper_url":"https://arxiv.org/abs/2010.14298v1","paper_title":"A Statistical Framework for Low-bitwidth Training of Deep Neural Networks","paper_date":"2020-10-27","code_links":[{"title":"cjf00000/StatQuant","url":"https://github.com/cjf00000/StatQuant"},{"title":"gaochang-bjtu/1-bit-fqt","url":"https://github.com/gaochang-bjtu/1-bit-fqt"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43516,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Heinsen Routing + RoBERTa-large","metrics":{"Accuracy":"96.0"},"paper_url":"https://arxiv.org/abs/2211.11754v3","paper_title":"An Algorithm for Routing Vectors in Sequences","paper_date":"2022-11-20","code_links":[{"title":"glassroom/heinsen_routing","url":"https://github.com/glassroom/heinsen_routing"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":1,"source":"archive","tags":[]},{"id":43517,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"MT-DNN","metrics":{"Accuracy":"95.6"},"paper_url":"https://arxiv.org/abs/1901.11504v2","paper_title":"Multi-Task Deep Neural Networks for Natural Language Understanding","paper_date":"2019-01-31","code_links":[{"title":"namisan/mt-dnn","url":"https://github.com/namisan/mt-dnn"},{"title":"xycforgithub/MultiTask-MRC","url":"https://github.com/xycforgithub/MultiTask-MRC"},{"title":"ABaldrati/MT-BERT","url":"https://github.com/ABaldrati/MT-BERT"},{"title":"phueb/CHILDES-SRL","url":"https://github.com/phueb/CHILDES-SRL"},{"title":"phueb/BabyBertSRL","url":"https://github.com/phueb/BabyBertSRL"},{"title":"om00839/machine-suneung","url":"https://github.com/om00839/machine-suneung"},{"title":"gaohuan2015/NLPTool","url":"https://github.com/gaohuan2015/NLPTool"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43518,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Heinsen Routing + GPT-2","metrics":{"Accuracy":"95.6"},"paper_url":"https://arxiv.org/abs/1911.00792v6","paper_title":"An Algorithm for Routing Capsules in All Domains","paper_date":"2019-11-02","code_links":[{"title":"glassroom/heinsen_routing","url":"https://github.com/glassroom/heinsen_routing"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":1,"source":"archive","tags":[]},{"id":43519,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"T5-Base","metrics":{"Accuracy":"95.2"},"paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","paper_date":"2019-10-23","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/t5"},{"title":"google-research/text-to-text-transfer-transformer","url":"https://github.com/google-research/text-to-text-transfer-transformer"},{"title":"amazon-science/chronos-forecasting","url":"https://github.com/amazon-science/chronos-forecasting"},{"title":"google-research/t5x","url":"https://github.com/google-research/t5x"},{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"thudm/swissarmytransformer","url":"https://github.com/thudm/swissarmytransformer"},{"title":"Ki6an/fastT5","url":"https://github.com/Ki6an/fastT5"},{"title":"google/seqio","url":"https://github.com/google/seqio"},{"title":"facebookresearch/atlas","url":"https://github.com/facebookresearch/atlas"},{"title":"conceptofmind/LaMDA-pytorch","url":"https://github.com/conceptofmind/LaMDA-pytorch"},{"title":"conceptofmind/lamda-rlhf-pytorch","url":"https://github.com/conceptofmind/lamda-rlhf-pytorch"},{"title":"thu-keg/omnievent","url":"https://github.com/thu-keg/omnievent"},{"title":"asahi417/lm-question-generation","url":"https://github.com/asahi417/lm-question-generation"},{"title":"abelriboulot/onnxt5","url":"https://github.com/abelriboulot/onnxt5"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"airc-keti/ke-t5","url":"https://github.com/airc-keti/ke-t5"},{"title":"yizhongw/tk-instruct","url":"https://github.com/yizhongw/tk-instruct"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"gulucaptain/dynamictrl","url":"https://github.com/gulucaptain/dynamictrl"},{"title":"google-research/t5x_retrieval","url":"https://github.com/google-research/t5x_retrieval"},{"title":"bigscience-workshop/architecture-objective","url":"https://github.com/bigscience-workshop/architecture-objective"},{"title":"dawn0815/UniSA","url":"https://github.com/dawn0815/UniSA"},{"title":"ibm/graph_ensemble_learning","url":"https://github.com/ibm/graph_ensemble_learning"},{"title":"wangcongcong123/ttt","url":"https://github.com/wangcongcong123/ttt"},{"title":"safakkbilici/Academic-Paper-Title-Recommendation","url":"https://github.com/safakkbilici/Academic-Paper-Title-Recommendation"},{"title":"bayer-science-for-a-better-life/data2text-bioleaflets","url":"https://github.com/bayer-science-for-a-better-life/data2text-bioleaflets"},{"title":"allenai/c4-documentation","url":"https://github.com/allenai/c4-documentation"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"lesterpjy/numeric-t5","url":"https://github.com/lesterpjy/numeric-t5"},{"title":"zhiqic/chartreader","url":"https://github.com/zhiqic/chartreader"},{"title":"LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer","url":"https://github.com/LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer"},{"title":"s-nlp/russe_detox_2022","url":"https://github.com/s-nlp/russe_detox_2022"},{"title":"skoltech-nlp/russe_detox_2022","url":"https://github.com/skoltech-nlp/russe_detox_2022"},{"title":"jongwooko/nash-pruning-official","url":"https://github.com/jongwooko/nash-pruning-official"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/t5"},{"title":"luomancs/retriever_reader_for_okvqa","url":"https://github.com/luomancs/retriever_reader_for_okvqa"},{"title":"qipengguo/p2_webnlg2020","url":"https://github.com/qipengguo/p2_webnlg2020"},{"title":"JunnYu/x-transformers-paddle","url":"https://github.com/JunnYu/x-transformers-paddle"},{"title":"Sharif-SLPL/t5-fa","url":"https://github.com/Sharif-SLPL/t5-fa"},{"title":"shivamraval98/multitask-t5_ae","url":"https://github.com/shivamraval98/multitask-t5_ae"},{"title":"junnyu/paddle_t5","url":"https://github.com/junnyu/paddle_t5"},{"title":"ChernovAndrey/chronos-forecasting-wasserstein","url":"https://github.com/ChernovAndrey/chronos-forecasting-wasserstein"},{"title":"cccntu/ft5-demo","url":"https://github.com/cccntu/ft5-demo"},{"title":"ArvinZhuang/BiTAG","url":"https://github.com/ArvinZhuang/BiTAG"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/t5"},{"title":"cccntu/ft5-demo-space","url":"https://github.com/cccntu/ft5-demo-space"},{"title":"xuetianci/pacit","url":"https://github.com/xuetianci/pacit"},{"title":"vgaraujov/seq2seq-spanish-plms","url":"https://github.com/vgaraujov/seq2seq-spanish-plms"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"thecodemasterk/Text-to-Text-transfer-transformers","url":"https://github.com/thecodemasterk/Text-to-Text-transfer-transformers"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/t5"},{"title":"KAGUYAHONGLAI/SRC","url":"https://github.com/KAGUYAHONGLAI/SRC"},{"title":"Nimesh-Patel/text-to-text-transfer-transformer","url":"https://github.com/Nimesh-Patel/text-to-text-transfer-transformer"},{"title":"souvikshanku/translit-former","url":"https://github.com/souvikshanku/translit-former"},{"title":"itzprashu1/prashant","url":"https://github.com/itzprashu1/prashant"},{"title":"2023-MindSpore-1/ms-code-164","url":"https://github.com/2023-MindSpore-1/ms-code-164"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43520,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"ERNIE 2.0 Base","metrics":{"Accuracy":"95"},"paper_url":"https://arxiv.org/abs/1907.12412v2","paper_title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","paper_date":"2019-07-29","code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-1.0"},{"title":"PaddlePaddle/ERNIE","url":"https://github.com/PaddlePaddle/ERNIE"},{"title":"DataScienceNigeria/ERNIE-2.0-from-Baidu-Inc.","url":"https://github.com/DataScienceNigeria/ERNIE-2.0-from-Baidu-Inc."}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43521,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"RoBERTa+DualCL","metrics":{"Accuracy":"94.91"},"paper_url":"https://arxiv.org/abs/2201.08702v1","paper_title":"Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation","paper_date":"2022-01-21","code_links":[{"title":"hiyouga/dual-contrastive-learning","url":"https://github.com/hiyouga/dual-contrastive-learning"},{"title":"hiyouga/hiyouga","url":"https://github.com/hiyouga/hiyouga"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43522,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"BERT-LARGE","metrics":{"Accuracy":"94.9"},"paper_url":"https://arxiv.org/abs/1810.04805v2","paper_title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","paper_date":"2018-10-11","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/nlp"},{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"google-research/bert","url":"https://github.com/google-research/bert"},{"title":"graykode/nlp-tutorial","url":"https://github.com/graykode/nlp-tutorial"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP"},{"title":"brightmart/text_classification","url":"https://github.com/brightmart/text_classification"},{"title":"PaddlePaddle/models","url":"https://github.com/PaddlePaddle/models"},{"title":"codertimo/BERT-pytorch","url":"https://github.com/codertimo/BERT-pytorch"},{"title":"bentrevett/pytorch-sentiment-analysis","url":"https://github.com/bentrevett/pytorch-sentiment-analysis"},{"title":"pytorch/text","url":"https://github.com/pytorch/text"},{"title":"shreyashankar/gpt3-sandbox","url":"https://github.com/shreyashankar/gpt3-sandbox"},{"title":"brightmart/roberta_zh","url":"https://github.com/brightmart/roberta_zh"},{"title":"dmlc/gluon-nlp","url":"https://github.com/dmlc/gluon-nlp"},{"title":"CyberZHG/keras-bert","url":"https://github.com/CyberZHG/keras-bert"},{"title":"alibaba/EasyNLP","url":"https://github.com/alibaba/EasyNLP"},{"title":"utterworks/fast-bert","url":"https://github.com/utterworks/fast-bert"},{"title":"kaushaltrivedi/fast-bert","url":"https://github.com/kaushaltrivedi/fast-bert"},{"title":"deepset-ai/FARM","url":"https://github.com/deepset-ai/FARM"},{"title":"ProsusAI/finBERT","url":"https://github.com/ProsusAI/finBERT"},{"title":"yoshitomo-matsubara/torchdistill","url":"https://github.com/yoshitomo-matsubara/torchdistill"},{"title":"Tencent/TurboTransformers","url":"https://github.com/Tencent/TurboTransformers"},{"title":"kyzhouhzau/BERT-NER","url":"https://github.com/kyzhouhzau/BERT-NER"},{"title":"kamalkraj/BERT_NER","url":"https://github.com/kamalkraj/BERT_NER"},{"title":"lonePatient/Bert-Multi-Label-Text-Classification","url":"https://github.com/lonePatient/Bert-Multi-Label-Text-Classification"},{"title":"Y1ran/NLP-BERT--ChineseVersion","url":"https://github.com/Y1ran/NLP-BERT--ChineseVersion"},{"title":"lukemelas/PyTorch-Pretrained-ViT","url":"https://github.com/lukemelas/PyTorch-Pretrained-ViT"},{"title":"kpe/bert-for-tf2","url":"https://github.com/kpe/bert-for-tf2"},{"title":"IndicoDataSolutions/finetune","url":"https://github.com/IndicoDataSolutions/finetune"},{"title":"Unbabel/COMET","url":"https://github.com/Unbabel/COMET"},{"title":"google-research/bigbird","url":"https://github.com/google-research/bigbird"},{"title":"dhlee347/pytorchic-bert","url":"https://github.com/dhlee347/pytorchic-bert"},{"title":"google/seqio","url":"https://github.com/google/seqio"},{"title":"re-search/DocProduct","url":"https://github.com/re-search/DocProduct"},{"title":"kpot/keras-transformer","url":"https://github.com/kpot/keras-transformer"},{"title":"imgarylai/bert-embedding","url":"https://github.com/imgarylai/bert-embedding"},{"title":"lemonhu/ner-bert-pytorch","url":"https://github.com/lemonhu/ner-bert-pytorch"},{"title":"R1j1t/contextualSpellCheck","url":"https://github.com/R1j1t/contextualSpellCheck"},{"title":"sberbank-ai/ner-bert","url":"https://github.com/sberbank-ai/ner-bert"},{"title":"kamalkraj/BERT-SQuAD","url":"https://github.com/kamalkraj/BERT-SQuAD"},{"title":"Microsoft/AzureML-BERT","url":"https://github.com/Microsoft/AzureML-BERT"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"thu-keg/omnievent","url":"https://github.com/thu-keg/omnievent"},{"title":"pengming617/bert_classification","url":"https://github.com/pengming617/bert_classification"},{"title":"awslabs/mlm-scoring","url":"https://github.com/awslabs/mlm-scoring"},{"title":"piegu/language-models","url":"https://github.com/piegu/language-models"},{"title":"charles9n/bert-sklearn","url":"https://github.com/charles9n/bert-sklearn"},{"title":"kyubyong/bert_ner","url":"https://github.com/kyubyong/bert_ner"},{"title":"louis-udm/ner-bert-crf","url":"https://github.com/louis-udm/ner-bert-crf"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"AtmaHou/MetaDialog","url":"https://github.com/AtmaHou/MetaDialog"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/bert"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/bert_thor"},{"title":"salesforce/GeDi","url":"https://github.com/salesforce/GeDi"},{"title":"helboukkouri/character-bert","url":"https://github.com/helboukkouri/character-bert"},{"title":"meelfy/pytorch_pretrained_bert","url":"https://github.com/meelfy/pytorch_pretrained_bert"},{"title":"google-deepmind/xquad","url":"https://github.com/google-deepmind/xquad"},{"title":"deepmind/xquad","url":"https://github.com/deepmind/xquad"},{"title":"BinWang28/BERT_Sentence_Embedding","url":"https://github.com/BinWang28/BERT_Sentence_Embedding"},{"title":"BinWang28/SBERT-WK-Sentence-Embedding","url":"https://github.com/BinWang28/SBERT-WK-Sentence-Embedding"},{"title":"glassroom/heinsen_routing","url":"https://github.com/glassroom/heinsen_routing"},{"title":"chiayewken/bert-qa","url":"https://github.com/chiayewken/bert-qa"},{"title":"chambliss/Multilingual_NER","url":"https://github.com/chambliss/Multilingual_NER"},{"title":"epfml/collaborative-attention","url":"https://github.com/epfml/collaborative-attention"},{"title":"manideep2510/siamese-BERT-fake-news-detection-LIAR","url":"https://github.com/manideep2510/siamese-BERT-fake-news-detection-LIAR"},{"title":"chujiezheng/ChID-Dataset","url":"https://github.com/chujiezheng/ChID-Dataset"},{"title":"zhengcj1/ChID-Dataset","url":"https://github.com/zhengcj1/ChID-Dataset"},{"title":"lvyufeng/mindspore-nlp-tutorial","url":"https://github.com/lvyufeng/mindspore-nlp-tutorial"},{"title":"wenhuchen/HDSA-Dialog","url":"https://github.com/wenhuchen/HDSA-Dialog"},{"title":"KeithGalli/pycon2020","url":"https://github.com/KeithGalli/pycon2020"},{"title":"ymcui/LAMB_Optimizer_TF","url":"https://github.com/ymcui/LAMB_Optimizer_TF"},{"title":"Sanyuan-Chen/RecAdam","url":"https://github.com/Sanyuan-Chen/RecAdam"},{"title":"mindspore-lab/mindnlp","url":"https://github.com/mindspore-lab/mindnlp/blob/master/mindnlp/models/bert/bert.py"},{"title":"ganeshjawahar/interpret_bert","url":"https://github.com/ganeshjawahar/interpret_bert"},{"title":"joongbo/tta","url":"https://github.com/joongbo/tta"},{"title":"dreamgonfly/BERT-pytorch","url":"https://github.com/dreamgonfly/BERT-pytorch"},{"title":"yifding/hetseq","url":"https://github.com/yifding/hetseq"},{"title":"musixmatchresearch/umberto","url":"https://github.com/musixmatchresearch/umberto"},{"title":"lonePatient/BERT-chinese-text-classification-pytorch","url":"https://github.com/lonePatient/BERT-chinese-text-classification-pytorch"},{"title":"athms/learning-from-brains","url":"https://github.com/athms/learning-from-brains"},{"title":"MLH-Fellowship/Social-BERTerfly","url":"https://github.com/MLH-Fellowship/Social-BERTerfly"},{"title":"Kyubyong/bert-token-embeddings","url":"https://github.com/Kyubyong/bert-token-embeddings"},{"title":"wzzzd/LM_NER","url":"https://github.com/wzzzd/LM_NER"},{"title":"writerai/fitbert","url":"https://github.com/writerai/fitbert"},{"title":"Qordobacode/fitbert","url":"https://github.com/Qordobacode/fitbert"},{"title":"okanvk/ENELPI---Soru-Cevap-Sistemi","url":"https://github.com/okanvk/ENELPI---Soru-Cevap-Sistemi"},{"title":"okanvk/Turkish-Reading-Comprehension-Question-Answering-Dataset","url":"https://github.com/okanvk/Turkish-Reading-Comprehension-Question-Answering-Dataset"},{"title":"whqwill/seq2seq-keyphrase-bert","url":"https://github.com/whqwill/seq2seq-keyphrase-bert"},{"title":"sagorbrur/bangla-bert","url":"https://github.com/sagorbrur/bangla-bert"},{"title":"avichaychriqui/HeBERT","url":"https://github.com/avichaychriqui/HeBERT"},{"title":"deepmipt/Slavic-BERT-NER","url":"https://github.com/deepmipt/Slavic-BERT-NER"},{"title":"reppy4620/Dialog","url":"https://github.com/reppy4620/Dialog"},{"title":"airsplay/vimpac","url":"https://github.com/airsplay/vimpac"},{"title":"huanghonggit/Mask-Language-Model","url":"https://github.com/huanghonggit/Mask-Language-Model"},{"title":"maknotavailable/pytorch-pretrained-bert","url":"https://github.com/maknotavailable/pytorch-pretrained-bert"},{"title":"Skumarr53/Attention-is-All-you-Need-PyTorch","url":"https://github.com/Skumarr53/Attention-is-All-you-Need-PyTorch"},{"title":"deping-1/2019-false-news-detection-challenge","url":"https://github.com/deping-1/2019-false-news-detection-challenge"},{"title":"lvyufeng/Cybertron","url":"https://github.com/lvyufeng/Cybertron/blob/master/cybertron/models/bert.py"},{"title":"babelscape/wikineural","url":"https://github.com/babelscape/wikineural"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms"},{"title":"aws-samples/amazon-sagemaker-bert-pytorch","url":"https://github.com/aws-samples/amazon-sagemaker-bert-pytorch"},{"title":"sajjjadayobi/ParsBigBird","url":"https://github.com/sajjjadayobi/ParsBigBird"},{"title":"CVxTz/music_genre_classification","url":"https://github.com/CVxTz/music_genre_classification"},{"title":"qywu/Chinese-GPT","url":"https://github.com/qywu/Chinese-GPT"},{"title":"phohenecker/pytorch-transformer","url":"https://github.com/phohenecker/pytorch-transformer"},{"title":"lonePatient/ERNIE-text-classification-pytorch","url":"https://github.com/lonePatient/ERNIE-text-classification-pytorch"},{"title":"IBM/MAX-Text-Sentiment-Classifier","url":"https://github.com/IBM/MAX-Text-Sentiment-Classifier"},{"title":"ericperfect/Bert_Position_BiLSTM_Attention_CRF_LSTMDecoder","url":"https://github.com/ericperfect/Bert_Position_BiLSTM_Attention_CRF_LSTMDecoder"},{"title":"duyunshu/bert-sentiment-analysis","url":"https://github.com/duyunshu/bert-sentiment-analysis"},{"title":"andi611/Mockingjay-Speech-Representation","url":"https://github.com/andi611/Mockingjay-Speech-Representation"},{"title":"SatyamSoni23/Smart-Question-Answering-System-on-Document","url":"https://github.com/SatyamSoni23/Smart-Question-Answering-System-on-Document"},{"title":"IBM/MAX-Toxic-Comment-Classifier","url":"https://github.com/IBM/MAX-Toxic-Comment-Classifier"},{"title":"ShivamRajSharma/Transformer-Architectures-From-Scratch","url":"https://github.com/ShivamRajSharma/Transformer-Architectures-From-Scratch"},{"title":"bit-ml/anoshift","url":"https://github.com/bit-ml/anoshift"},{"title":"skoltech-nlp/rudetoxifier","url":"https://github.com/skoltech-nlp/rudetoxifier"},{"title":"lonePatient/bert-sentence-similarity-pytorch","url":"https://github.com/lonePatient/bert-sentence-similarity-pytorch"},{"title":"tugstugi/mongolian-bert","url":"https://github.com/tugstugi/mongolian-bert"},{"title":"TeamLab/bert-gcn-for-paper-citation","url":"https://github.com/TeamLab/bert-gcn-for-paper-citation"},{"title":"wzzzd/Pretrain_Bert_with_MaskLM","url":"https://github.com/wzzzd/Pretrain_Bert_with_MaskLM"},{"title":"anton-bushuiev/ppiformer","url":"https://github.com/anton-bushuiev/ppiformer"},{"title":"Karthik-Bhaskar/Context-Based-Question-Answering","url":"https://github.com/Karthik-Bhaskar/Context-Based-Question-Answering"},{"title":"KomorebiLHX/Emotion-Recognition-in-Conversations","url":"https://github.com/KomorebiLHX/Emotion-Recognition-in-Conversations"},{"title":"stefan-it/europeana-bert","url":"https://github.com/stefan-it/europeana-bert"},{"title":"wangcongcong123/ttt","url":"https://github.com/wangcongcong123/ttt"},{"title":"khalidsaifullaah/bertify","url":"https://github.com/khalidsaifullaah/bertify"},{"title":"benywon/ReCO","url":"https://github.com/benywon/ReCO"},{"title":"thunlp/ReInfoSelect","url":"https://github.com/thunlp/ReInfoSelect"},{"title":"noise-learning/selfmix","url":"https://github.com/noise-learning/selfmix"},{"title":"lyccol/CodeBERT-based-webshell-detection","url":"https://github.com/lyccol/CodeBERT-based-webshell-detection"},{"title":"sagorbrur/codeswitch","url":"https://github.com/sagorbrur/codeswitch"},{"title":"KnightZhang625/BERT_TF","url":"https://github.com/KnightZhang625/BERT_TF"},{"title":"Farahn/AES","url":"https://github.com/Farahn/AES"},{"title":"geondopark/ckd","url":"https://github.com/geondopark/ckd"},{"title":"IBM/MAX-Question-Answering","url":"https://github.com/IBM/MAX-Question-Answering"},{"title":"benywon/ChiQA","url":"https://github.com/benywon/ChiQA"},{"title":"AdamStein97/Semi-Supervised-BERT-NER","url":"https://github.com/AdamStein97/Semi-Supervised-BERT-NER"},{"title":"LorenzoAgnolucci/BERT_for_ABSA","url":"https://github.com/LorenzoAgnolucci/BERT_for_ABSA"},{"title":"devJWSong/bert-crf-entity-recognition-pytorch","url":"https://github.com/devJWSong/bert-crf-entity-recognition-pytorch"},{"title":"ypeleg/MinimalIsAllYouNeed","url":"https://github.com/ypeleg/MinimalIsAllYouNeed"},{"title":"ilhamfp/indonesian-text-classification-multilingual","url":"https://github.com/ilhamfp/indonesian-text-classification-multilingual"},{"title":"sunyilgdx/prompts4keras","url":"https://github.com/sunyilgdx/prompts4keras"},{"title":"AutomatedProgramRepair-2021/dear-auto-fix","url":"https://github.com/AutomatedProgramRepair-2021/dear-auto-fix"},{"title":"Impavidity/relogic","url":"https://github.com/Impavidity/relogic"},{"title":"MalteHB/-l-ctra","url":"https://github.com/MalteHB/-l-ctra"},{"title":"octanove/grammartagger","url":"https://github.com/octanove/grammartagger"},{"title":"abhilash1910/BERTSimilarity","url":"https://github.com/abhilash1910/BERTSimilarity"},{"title":"overfitter/biobert_embedding","url":"https://github.com/overfitter/biobert_embedding"},{"title":"linlei1214/SITS-BERT","url":"https://github.com/linlei1214/SITS-BERT"},{"title":"benywon/ChineseBert","url":"https://github.com/benywon/ChineseBert"},{"title":"brightmart/bert_customized","url":"https://github.com/brightmart/bert_customized"},{"title":"uva-dsa/ems-pipeline","url":"https://github.com/uva-dsa/ems-pipeline"},{"title":"ElizaLo/Question-Answering-based-on-SQuAD","url":"https://github.com/ElizaLo/Question-Answering-based-on-SQuAD"},{"title":"af-ai-center/nerblackbox","url":"https://github.com/af-ai-center/nerblackbox"},{"title":"flxst/nerblackbox","url":"https://github.com/flxst/nerblackbox"},{"title":"SkullFang/BERT_NLP_Classification","url":"https://github.com/SkullFang/BERT_NLP_Classification"},{"title":"GauthierDmn/question_answering","url":"https://github.com/GauthierDmn/question_answering"},{"title":"ABaldrati/MT-BERT","url":"https://github.com/ABaldrati/MT-BERT"},{"title":"Colanim/BERT_STS-B","url":"https://github.com/Colanim/BERT_STS-B"},{"title":"guoyaohua/BERT-Chinese-Annotation","url":"https://github.com/guoyaohua/BERT-Chinese-Annotation"},{"title":"Kanishkparganiha/Named-Entity-Recognition-using-BERT-with-PyTorch","url":"https://github.com/Kanishkparganiha/Named-Entity-Recognition-using-BERT-with-PyTorch"},{"title":"mkavim/finetune_bert","url":"https://github.com/mkavim/finetune_bert"},{"title":"guoyaohua/BERT-Classifier","url":"https://github.com/guoyaohua/BERT-Classifier"},{"title":"HuihuiChyan/BJTUNLP_Practice2020","url":"https://github.com/HuihuiChyan/BJTUNLP_Practice2020"},{"title":"stefan-it/historic-ner","url":"https://github.com/stefan-it/historic-ner"},{"title":"baotramduong/Sentiment-Analysis-with-Deep-Learning-using-BERT","url":"https://github.com/baotramduong/Sentiment-Analysis-with-Deep-Learning-using-BERT"},{"title":"dbmdz/historic-ner","url":"https://github.com/dbmdz/historic-ner"},{"title":"baotramduong/Twitter-Sentiment-Analysis-with-Deep-Learning-using-BERT","url":"https://github.com/baotramduong/Twitter-Sentiment-Analysis-with-Deep-Learning-using-BERT"},{"title":"MansMeg/IntroML","url":"https://github.com/MansMeg/IntroML"},{"title":"bino282/bert4news","url":"https://github.com/bino282/bert4news"},{"title":"benywon/ComQA","url":"https://github.com/benywon/ComQA"},{"title":"madhawav/MML","url":"https://github.com/madhawav/MML"},{"title":"uygarkurt/BERT-PyTorch","url":"https://github.com/uygarkurt/BERT-PyTorch"},{"title":"xiangyue9607/CliniRC","url":"https://github.com/xiangyue9607/CliniRC"},{"title":"SindhuMadi/FakeNewsDetection","url":"https://github.com/SindhuMadi/FakeNewsDetection"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/bert"},{"title":"ambityga/memsem","url":"https://github.com/ambityga/memsem"},{"title":"debnsuma/Intro-Transformer-BERT","url":"https://github.com/debnsuma/Intro-Transformer-BERT"},{"title":"cybertronai/megatron-lm","url":"https://github.com/cybertronai/megatron-lm"},{"title":"smarton-empower/smarton-ai","url":"https://github.com/smarton-empower/smarton-ai"},{"title":"SAP-samples/acl2019-commonsense","url":"https://github.com/SAP-samples/acl2019-commonsense"},{"title":"SAP-samples/acl2019-commonsense-reasoning","url":"https://github.com/SAP-samples/acl2019-commonsense-reasoning"},{"title":"lcs2-iiitd/emotion-flip-reasoning","url":"https://github.com/lcs2-iiitd/emotion-flip-reasoning"},{"title":"han-shi/SparseBERT","url":"https://github.com/han-shi/SparseBERT"},{"title":"davidbellamy/labrador","url":"https://github.com/davidbellamy/labrador"},{"title":"heraclex12/vietpunc","url":"https://github.com/heraclex12/vietpunc"},{"title":"DimasDMM/nlp-completer","url":"https://github.com/DimasDMM/nlp-completer"},{"title":"af-ai-center/bert","url":"https://github.com/af-ai-center/bert"},{"title":"Jackma3/NER-Bert-BiLstm","url":"https://github.com/Jackma3/NER-Bert-BiLstm"},{"title":"eagle705/bert","url":"https://github.com/eagle705/bert"},{"title":"DimasDMM/transformers","url":"https://github.com/DimasDMM/transformers"},{"title":"fancyerii/bert","url":"https://github.com/fancyerii/bert"},{"title":"cedrickchee/pytorch-pretrained-BERT","url":"https://github.com/cedrickchee/pytorch-pretrained-BERT"},{"title":"Susheel-1999/Sentence_Similarity","url":"https://github.com/Susheel-1999/Sentence_Similarity"},{"title":"xiaopingzhong/bert-finetune-for-classfier","url":"https://github.com/xiaopingzhong/bert-finetune-for-classfier"},{"title":"SYangDong/bert-with-frozen-code","url":"https://github.com/SYangDong/bert-with-frozen-code"},{"title":"tree-park/bert-pretrainer","url":"https://github.com/tree-park/bert-pretrainer"},{"title":"abhilashreddys/Fake-News-Article","url":"https://github.com/abhilashreddys/Fake-News-Article"},{"title":"autobotasia/vibert","url":"https://github.com/autobotasia/vibert"},{"title":"rasta-nitzsche/Bert-For-Algerian-Dialect-DariBERTo","url":"https://github.com/rasta-nitzsche/Bert-For-Algerian-Dialect-DariBERTo"},{"title":"tobyatgithub/bert_tutorial","url":"https://github.com/tobyatgithub/bert_tutorial"},{"title":"Holldean/BERT-Pruning","url":"https://github.com/Holldean/BERT-Pruning"},{"title":"mindspore-courses/ABSA-MindSpore","url":"https://github.com/mindspore-courses/ABSA-MindSpore"},{"title":"theneuralbeing/bert-finetuning-webinar","url":"https://github.com/theneuralbeing/bert-finetuning-webinar"},{"title":"HuihuiChyan/BJTUNLP_Practice2021","url":"https://github.com/HuihuiChyan/BJTUNLP_Practice2021"},{"title":"nerdimite/bert-finetuning-webinar","url":"https://github.com/nerdimite/bert-finetuning-webinar"},{"title":"soutsios/pos-tagger-bert-tensorflow","url":"https://github.com/soutsios/pos-tagger-bert-tensorflow"},{"title":"hate-alert/indicabusive","url":"https://github.com/hate-alert/indicabusive"},{"title":"viniciusoliveirasd/bert-applications","url":"https://github.com/viniciusoliveirasd/bert-applications"},{"title":"EssayKillerBrain/NLP-BERT-Chinese","url":"https://github.com/EssayKillerBrain/NLP-BERT-Chinese"},{"title":"lehoanganh298/BERT-Question-Answering","url":"https://github.com/lehoanganh298/BERT-Question-Answering"},{"title":"derronxu/sparsebert","url":"https://github.com/derronxu/sparsebert"},{"title":"kelly2016/multi-label-bert","url":"https://github.com/kelly2016/multi-label-bert"},{"title":"nicolashernandez/readi-lrec22","url":"https://github.com/nicolashernandez/readi-lrec22"},{"title":"circlePi/BERT_Chinese_Text_Class_By_pytorch","url":"https://github.com/circlePi/BERT_Chinese_Text_Class_By_pytorch"},{"title":"gcunhase/embracebert","url":"https://github.com/gcunhase/embracebert"},{"title":"zer0sh0t/artificial_intelligence","url":"https://github.com/zer0sh0t/artificial_intelligence/tree/master/language_models/bidirectional_encoder_representations_from_transformers"},{"title":"anupamsingh610/bert_ner_stride","url":"https://github.com/anupamsingh610/bert_ner_stride"},{"title":"itsShnik/adaptively-finetuning-transformers","url":"https://github.com/itsShnik/adaptively-finetuning-transformers"},{"title":"DylanCope/Image-Captioning-with-Bimodal-Transformers","url":"https://github.com/DylanCope/Image-Captioning-with-Bimodal-Transformers"},{"title":"sydney-machine-learning/sentimentanalysis-uselections","url":"https://github.com/sydney-machine-learning/sentimentanalysis-uselections"},{"title":"arkel23/PyTorch-Pretrained-ViT","url":"https://github.com/arkel23/PyTorch-Pretrained-ViT"},{"title":"hegebharat/sentiment-Analysis-for-German-Datasets","url":"https://github.com/hegebharat/sentiment-Analysis-for-German-Datasets"},{"title":"deepmipt/bert","url":"https://github.com/deepmipt/bert/tree/feat/multi_gpu"},{"title":"ManasRMohanty/DS5500-capstone","url":"https://github.com/ManasRMohanty/DS5500-capstone"},{"title":"Raman-Raje/Machine-Reading-Comprehension-Neural-Question-Answer-","url":"https://github.com/Raman-Raje/Machine-Reading-Comprehension-Neural-Question-Answer-"},{"title":"karta282950/bert-multiclass","url":"https://github.com/karta282950/bert-multiclass"},{"title":"om00839/machine-suneung","url":"https://github.com/om00839/machine-suneung"},{"title":"jungomi/swiss-language-model","url":"https://github.com/jungomi/swiss-language-model"},{"title":"fanchenyou/transformer-study","url":"https://github.com/fanchenyou/transformer-study"},{"title":"asgaardlab/test-case-similarity-technique","url":"https://github.com/asgaardlab/test-case-similarity-technique"},{"title":"rajlm10/Chandler","url":"https://github.com/rajlm10/Chandler"},{"title":"harenlin/IMDB-Sentiment-Analysis-Using-BERT-Fine-Tuning","url":"https://github.com/harenlin/IMDB-Sentiment-Analysis-Using-BERT-Fine-Tuning"},{"title":"noelkelias/multitok","url":"https://github.com/noelkelias/multitok"},{"title":"2miatran/Natural-Language-Processing","url":"https://github.com/2miatran/Natural-Language-Processing"},{"title":"arielsho/decomposition-table-reasoning","url":"https://github.com/arielsho/decomposition-table-reasoning"},{"title":"scotthlee/injury_autocoding","url":"https://github.com/scotthlee/injury_autocoding"},{"title":"broccolik/BERT-NER","url":"https://github.com/broccolik/BERT-NER"},{"title":"abhaskumarsinha/Keras-implementation-of-Transformer-Architecture","url":"https://github.com/abhaskumarsinha/Keras-implementation-of-Transformer-Architecture"},{"title":"vmware-labs/bert-pretraining","url":"https://github.com/vmware-labs/bert-pretraining"},{"title":"RonRaifer/BERT-Ghazali","url":"https://github.com/RonRaifer/BERT-Ghazali"},{"title":"kobowon/cs470_project_version2","url":"https://github.com/kobowon/cs470_project_version2"},{"title":"venkyr91193/Sentiment-Analysis-with-BERT","url":"https://github.com/venkyr91193/Sentiment-Analysis-with-BERT"},{"title":"ltgoslo/assessing_and_probing_sentiment","url":"https://github.com/ltgoslo/assessing_and_probing_sentiment"},{"title":"LeoWood/bert-horovod","url":"https://github.com/LeoWood/bert-horovod"},{"title":"mocherson/aki_bert","url":"https://github.com/mocherson/aki_bert"},{"title":"polzinben/TensorFlow_NLP","url":"https://github.com/polzinben/TensorFlow_NLP"},{"title":"siramatu/brigade-visualizer","url":"https://github.com/siramatu/brigade-visualizer"},{"title":"samirsahoo007/Audio-and-Speech-Processing","url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing"},{"title":"Doffery/BERT-Sentiment-Analysis-Amazon-Review","url":"https://github.com/Doffery/BERT-Sentiment-Analysis-Amazon-Review"},{"title":"venkyr91193/Sentiment_Analysis_with_BERT","url":"https://github.com/venkyr91193/Sentiment_Analysis_with_BERT"},{"title":"why2000/DuReader-bert","url":"https://github.com/why2000/DuReader-bert"},{"title":"weidafeng/NLU2019","url":"https://github.com/weidafeng/NLU2019"},{"title":"theQuert/inlpfun","url":"https://github.com/theQuert/inlpfun"},{"title":"johnr0/TaleBrush-backend","url":"https://github.com/johnr0/TaleBrush-backend"},{"title":"Jun-Zhang-32108/Sentiment-Analysis","url":"https://github.com/Jun-Zhang-32108/Sentiment-Analysis"},{"title":"MS-Mind/MS-Code-01","url":"https://github.com/MS-Mind/MS-Code-01/tree/main/soft_masked_bert"},{"title":"gouwenrui/cpe-pro-main","url":"https://github.com/gouwenrui/cpe-pro-main"},{"title":"2024-MindSpore-1/Code3","url":"https://github.com/2024-MindSpore-1/Code3/tree/main/scBERT"},{"title":"hoangtrungchinh/Bert-SQuAD-v2","url":"https://github.com/hoangtrungchinh/Bert-SQuAD-v2"},{"title":"nageshsinghc4/deepwrap","url":"https://github.com/nageshsinghc4/deepwrap"},{"title":"ArvinZhuang/BiTAG","url":"https://github.com/ArvinZhuang/BiTAG"},{"title":"eaishwa/quora-ques-pair-similarity","url":"https://github.com/eaishwa/quora-ques-pair-similarity"},{"title":"rohanshad/cmr_transformer","url":"https://github.com/rohanshad/cmr_transformer"},{"title":"MichaelZhouwang/LMlexsub","url":"https://github.com/MichaelZhouwang/LMlexsub"},{"title":"the-Quert/iNLPfun","url":"https://github.com/the-Quert/iNLPfun"},{"title":"Coda-s/BJTU_NLP_Practice","url":"https://github.com/Coda-s/BJTU_NLP_Practice"},{"title":"goldenbili/bert_lamb_pretrain","url":"https://github.com/goldenbili/bert_lamb_pretrain"},{"title":"MaZhiyuanBUAA/bert-tf1.4.0","url":"https://github.com/MaZhiyuanBUAA/bert-tf1.4.0"},{"title":"dispink/xpt","url":"https://github.com/dispink/xpt"},{"title":"mirbostani/QA-KD-AL","url":"https://github.com/mirbostani/QA-KD-AL"},{"title":"abhineet/sentence_classification_pubmed_scibert","url":"https://github.com/abhineet/sentence_classification_pubmed_scibert"},{"title":"frankcgq105/BERTCHEN","url":"https://github.com/frankcgq105/BERTCHEN"},{"title":"Kerram/Deephol-Bert-Zpp","url":"https://github.com/Kerram/Deephol-Bert-Zpp"},{"title":"cospplay/bert-master","url":"https://github.com/cospplay/bert-master"},{"title":"YuanEric88/bert-nlu","url":"https://github.com/YuanEric88/bert-nlu"},{"title":"yuelinan/c3vg","url":"https://github.com/yuelinan/c3vg"},{"title":"Domminique/Deploy-BERT-for-Sentiment-Analysis-with-FastAPI-","url":"https://github.com/Domminique/Deploy-BERT-for-Sentiment-Analysis-with-FastAPI-"},{"title":"scut-bds/example_repo_from_scutbds","url":"https://github.com/scut-bds/example_repo_from_scutbds"},{"title":"Alihassan7726/Multi-Class-classification-using-BERT-","url":"https://github.com/Alihassan7726/Multi-Class-classification-using-BERT-"},{"title":"kriesbeck/masked-language-prediction","url":"https://github.com/kriesbeck/masked-language-prediction"},{"title":"IMPLabUniPr/UniParma-at-semeval-2021-task-5","url":"https://github.com/IMPLabUniPr/UniParma-at-semeval-2021-task-5"},{"title":"SumitM0432/Quora-Insincere-Questions-Classification","url":"https://github.com/SumitM0432/Quora-Insincere-Questions-Classification"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/bert"},{"title":"AbhishekD15/Sentiment-Analysis_BERT","url":"https://github.com/AbhishekD15/Sentiment-Analysis_BERT"},{"title":"Misoknisky/Bert-MultiGpu","url":"https://github.com/Misoknisky/Bert-MultiGpu"},{"title":"thethirdwheel/malumagraph","url":"https://github.com/thethirdwheel/malumagraph"},{"title":"cmunnis/BERT_vs_Transformer-XL","url":"https://github.com/cmunnis/BERT_vs_Transformer-XL"},{"title":"brightmart/bert_original","url":"https://github.com/brightmart/bert_original"},{"title":"JNUpython/bert","url":"https://github.com/JNUpython/bert"},{"title":"Zeeshan75/Bert_Telugu_Ner","url":"https://github.com/Zeeshan75/Bert_Telugu_Ner"},{"title":"AGiannoutsos/COVID19-document-retrieval-with-BERT","url":"https://github.com/AGiannoutsos/COVID19-document-retrieval-with-BERT"},{"title":"BirgerMoell/bertcastle","url":"https://github.com/BirgerMoell/bertcastle"},{"title":"BroCoLySTyLe/SQLovaReview","url":"https://github.com/BroCoLySTyLe/SQLovaReview"},{"title":"tornermarton/bert-keras","url":"https://github.com/tornermarton/bert-keras"},{"title":"YongWookHa/BERT-on-Pytorch-Template","url":"https://github.com/YongWookHa/BERT-on-Pytorch-Template"},{"title":"yanzhitech/bert","url":"https://github.com/yanzhitech/bert"},{"title":"common-english/bert-all","url":"https://github.com/common-english/bert-all"},{"title":"JMSaindon/NlpSquad","url":"https://github.com/JMSaindon/NlpSquad"},{"title":"amauriciorr/AubreyBot","url":"https://github.com/amauriciorr/AubreyBot"},{"title":"Nilanshrajput/Intent_classification","url":"https://github.com/Nilanshrajput/Intent_classification"},{"title":"wyf-python/Bert-Pytorch-TextClassification","url":"https://github.com/wyf-python/Bert-Pytorch-TextClassification"},{"title":"teghub/TurkishNER-BERT","url":"https://github.com/teghub/TurkishNER-BERT"},{"title":"SpikeKing/My-Bert","url":"https://github.com/SpikeKing/My-Bert"},{"title":"sonalisrijan/Deep-Learning-based-Defect-Prediction-Model-for-Source-Code","url":"https://github.com/sonalisrijan/Deep-Learning-based-Defect-Prediction-Model-for-Source-Code"},{"title":"avishek-018/single_notebook_projects","url":"https://github.com/avishek-018/single_notebook_projects"},{"title":"gbcolborne/lang_id","url":"https://github.com/gbcolborne/lang_id"},{"title":"krantirk/BERT-Pretrained-model","url":"https://github.com/krantirk/BERT-Pretrained-model"},{"title":"saravanakumarjsk/BERT-collection","url":"https://github.com/saravanakumarjsk/BERT-collection"},{"title":"Katsumata420/bert_mlm","url":"https://github.com/Katsumata420/bert_mlm"},{"title":"socc-io/piqaboo","url":"https://github.com/socc-io/piqaboo"},{"title":"a414351664/Bert_MRC","url":"https://github.com/a414351664/Bert_MRC"},{"title":"zaaztt/bert_chinese_example","url":"https://github.com/zaaztt/bert_chinese_example"},{"title":"mayurnewase/Quora-Bert","url":"https://github.com/mayurnewase/Quora-Bert"},{"title":"Eeun-ju/NLP-study","url":"https://github.com/Eeun-ju/NLP-study"},{"title":"ricardordb/bert","url":"https://github.com/ricardordb/bert"},{"title":"luckynozomi/PPI_Bert","url":"https://github.com/luckynozomi/PPI_Bert"},{"title":"surancy/nlp-classification-with-BERT","url":"https://github.com/surancy/nlp-classification-with-BERT"},{"title":"hoichunlaw/COVID-BERT","url":"https://github.com/hoichunlaw/COVID-BERT"},{"title":"evtaktasheva/dependency_extraction","url":"https://github.com/evtaktasheva/dependency_extraction"},{"title":"flyliu2017/bert","url":"https://github.com/flyliu2017/bert"},{"title":"Guowei-Yan/Data","url":"https://github.com/Guowei-Yan/Data"},{"title":"h4ste/oscar","url":"https://github.com/h4ste/oscar"},{"title":"lkfo415579/MT-Readling-List","url":"https://github.com/lkfo415579/MT-Readling-List"},{"title":"vanslerry/long_text","url":"https://github.com/vanslerry/long_text"},{"title":"debnsuma/AmazonSageMaker101","url":"https://github.com/debnsuma/AmazonSageMaker101"},{"title":"jsantoso2/yelp-clone-ml-project","url":"https://github.com/jsantoso2/yelp-clone-ml-project"},{"title":"goldenbili/Bert_Test3","url":"https://github.com/goldenbili/Bert_Test3"},{"title":"coco60/bert-test","url":"https://github.com/coco60/bert-test"},{"title":"vanpersie32/Multigpu-Bert","url":"https://github.com/vanpersie32/Multigpu-Bert"},{"title":"danlim-wz/analysis_of_social_media_data_about_singapore","url":"https://github.com/danlim-wz/analysis_of_social_media_data_about_singapore"},{"title":"nicholasbao/nlp_job","url":"https://github.com/nicholasbao/nlp_job"},{"title":"shaikhzhas/bert","url":"https://github.com/shaikhzhas/bert"},{"title":"somiltg/xquad","url":"https://github.com/somiltg/xquad"},{"title":"xbtlin/All-about-Machine-Learning","url":"https://github.com/xbtlin/All-about-Machine-Learning"},{"title":"meizi1114/bert","url":"https://github.com/meizi1114/bert"},{"title":"ufal/wembedding_service","url":"https://github.com/ufal/wembedding_service"},{"title":"nmfisher/bert-modified","url":"https://github.com/nmfisher/bert-modified"},{"title":"JA-Bar/nlp-depression","url":"https://github.com/JA-Bar/nlp-depression"},{"title":"OweysMomenzada/Evergreen-Content-Classifier-for-german-Text","url":"https://github.com/OweysMomenzada/Evergreen-Content-Classifier-for-german-Text"},{"title":"wchh127/yykf","url":"https://github.com/wchh127/yykf"},{"title":"nalbarr/coursera-ai4med-course3","url":"https://github.com/nalbarr/coursera-ai4med-course3"},{"title":"appcoreopc/berty","url":"https://github.com/appcoreopc/berty"},{"title":"fabiocorreacordeiro/Elsevier_abstracts-Classification","url":"https://github.com/fabiocorreacordeiro/Elsevier_abstracts-Classification"},{"title":"Nstats/my_bert","url":"https://github.com/Nstats/my_bert"},{"title":"LoveYang/bert_test","url":"https://github.com/LoveYang/bert_test"},{"title":"mohamedateya/bert-fine-tuning-sentence-classification-for-cola","url":"https://github.com/mohamedateya/bert-fine-tuning-sentence-classification-for-cola"},{"title":"qbxlvnf11/pretrained-language-model-BERT","url":"https://github.com/qbxlvnf11/pretrained-language-model-BERT"},{"title":"davidsvaughn/dts-tf","url":"https://github.com/davidsvaughn/dts-tf"},{"title":"Alihassan7726/Fine-tuning-BERT-for-semantic-sentence-pairs-classification","url":"https://github.com/Alihassan7726/Fine-tuning-BERT-for-semantic-sentence-pairs-classification"},{"title":"xiuyu0000/tutorials","url":"https://github.com/xiuyu0000/tutorials/tree/main/bert"},{"title":"habibullah-araphat/BERT-NER-TPU","url":"https://github.com/habibullah-araphat/BERT-NER-TPU"},{"title":"RxstydnR/Stock_BERT","url":"https://github.com/RxstydnR/Stock_BERT"},{"title":"Vladimetr/ASR-Knowledge-Transferring","url":"https://github.com/Vladimetr/ASR-Knowledge-Transferring"},{"title":"AhmedYounes94/Semi-supervised-BERT-NER","url":"https://github.com/AhmedYounes94/Semi-supervised-BERT-NER"},{"title":"mtzcorporations/nlp_teamjodka","url":"https://github.com/mtzcorporations/nlp_teamjodka"},{"title":"darr/nerbert","url":"https://github.com/darr/nerbert"},{"title":"EuphoriaYan/bert_component","url":"https://github.com/EuphoriaYan/bert_component"},{"title":"Hibb-bb/ALLM","url":"https://github.com/Hibb-bb/ALLM"},{"title":"bcaitech1/p2-klue-Heeseok-Jeong","url":"https://github.com/bcaitech1/p2-klue-Heeseok-Jeong"},{"title":"binhetech/bert-application","url":"https://github.com/binhetech/bert-application"},{"title":"hegebharat/SelfDiscovery","url":"https://github.com/hegebharat/SelfDiscovery"},{"title":"Chonwai/Learning_BERT","url":"https://github.com/Chonwai/Learning_BERT"},{"title":"tdd-ai/data-collection","url":"https://github.com/tdd-ai/data-collection"},{"title":"MINGG2333/bert_ms","url":"https://github.com/MINGG2333/bert_ms"},{"title":"junhahyung/bert_finetune","url":"https://github.com/junhahyung/bert_finetune"},{"title":"Kosuke-Szk/BERT-NER-ja","url":"https://github.com/Kosuke-Szk/BERT-NER-ja"},{"title":"jageshmaharjan/BERT_Service","url":"https://github.com/jageshmaharjan/BERT_Service"},{"title":"MarcosGrzeca/drunktweets","url":"https://github.com/MarcosGrzeca/drunktweets"},{"title":"jiyuan/ainote","url":"https://github.com/jiyuan/ainote"},{"title":"qbxlvnf11/contextualized-embedding-BERT","url":"https://github.com/qbxlvnf11/contextualized-embedding-BERT"},{"title":"TOSHISTATS/Classification-of-Japanese-news-with-BERT","url":"https://github.com/TOSHISTATS/Classification-of-Japanese-news-with-BERT"},{"title":"samwisegamjeee/pytorch-transformers","url":"https://github.com/samwisegamjeee/pytorch-transformers"},{"title":"lennonzurich/lalala","url":"https://github.com/lennonzurich/lalala"},{"title":"qbxlvnf11/BERT","url":"https://github.com/qbxlvnf11/BERT"},{"title":"Nstats/bert_senti_analysis_ch","url":"https://github.com/Nstats/bert_senti_analysis_ch"},{"title":"flyliu2017/bert_modularized","url":"https://github.com/flyliu2017/bert_modularized"},{"title":"xuzhezhaozhao/bert_reading","url":"https://github.com/xuzhezhaozhao/bert_reading"},{"title":"kiko441500/google_bert","url":"https://github.com/kiko441500/google_bert"},{"title":"abhiagg92/bert_sentiment","url":"https://github.com/abhiagg92/bert_sentiment"},{"title":"Zehui127/SQUAD_BERT","url":"https://github.com/Zehui127/SQUAD_BERT"},{"title":"UnknownGenie/altered-BERT-KPE","url":"https://github.com/UnknownGenie/altered-BERT-KPE"},{"title":"guzhang480/Google_BERT","url":"https://github.com/guzhang480/Google_BERT"},{"title":"RenXiangyuan/tf_bert","url":"https://github.com/RenXiangyuan/tf_bert"},{"title":"crx934080895/Bert-CRF_New2","url":"https://github.com/crx934080895/Bert-CRF_New2"},{"title":"diabhaque/Sixth-Sense","url":"https://github.com/diabhaque/Sixth-Sense"},{"title":"zaradana/Fast_BERT","url":"https://github.com/zaradana/Fast_BERT"},{"title":"itspreeti25/Q-A-implementation-using-BERT-finetuned-on-multiple-datasets","url":"https://github.com/itspreeti25/Q-A-implementation-using-BERT-finetuned-on-multiple-datasets"},{"title":"gggggeun/DeepLearning_Architecture","url":"https://github.com/gggggeun/DeepLearning_Architecture"},{"title":"aaronHuang0121/AI-CUP-2020","url":"https://github.com/aaronHuang0121/AI-CUP-2020"},{"title":"pisalore/roberta_results","url":"https://github.com/pisalore/roberta_results"},{"title":"rohan400/PepperQA","url":"https://github.com/rohan400/PepperQA"},{"title":"StoneGH/bert","url":"https://github.com/StoneGH/bert"},{"title":"xiaopp123/bert_explain","url":"https://github.com/xiaopp123/bert_explain"},{"title":"JeheonPark596/sentimentsurvival","url":"https://github.com/JeheonPark596/sentimentsurvival"},{"title":"Xinsen-Zhang/transformer","url":"https://github.com/Xinsen-Zhang/transformer"},{"title":"MOHAMEDELDAKDOUKY/bert_adjusted","url":"https://github.com/MOHAMEDELDAKDOUKY/bert_adjusted"},{"title":"StuartCHAN/KARL","url":"https://github.com/StuartCHAN/KARL"},{"title":"goodluck4s/bert-","url":"https://github.com/goodluck4s/bert-"},{"title":"thecodemasterk/BERT","url":"https://github.com/thecodemasterk/BERT"},{"title":"dzqjorking/transpose","url":"https://github.com/dzqjorking/transpose"},{"title":"pingheng001/Cnn-Bert","url":"https://github.com/pingheng001/Cnn-Bert"},{"title":"TheNeuromancer/SentEmb","url":"https://github.com/TheNeuromancer/SentEmb"},{"title":"Arthurizijar/Bert_Airport","url":"https://github.com/Arthurizijar/Bert_Airport"},{"title":"MatthewSwahn/news-headlines-sarcasm-detector","url":"https://github.com/MatthewSwahn/news-headlines-sarcasm-detector"},{"title":"epcpu/deep-nlp-links","url":"https://github.com/epcpu/deep-nlp-links"},{"title":"chunghyunhee/twitter_disaster_NLP","url":"https://github.com/chunghyunhee/twitter_disaster_NLP"},{"title":"XINZXZHANG/Bert_repo","url":"https://github.com/XINZXZHANG/Bert_repo"},{"title":"yuhangT/tf_bert","url":"https://github.com/yuhangT/tf_bert"},{"title":"mithunpaul08/bert_tensorflow","url":"https://github.com/mithunpaul08/bert_tensorflow"},{"title":"DeligientSloth/bert-tensorflow","url":"https://github.com/DeligientSloth/bert-tensorflow"},{"title":"chandu7077/mybert","url":"https://github.com/chandu7077/mybert"},{"title":"darr/nlp_work","url":"https://github.com/darr/nlp_work"},{"title":"halo090770/bert","url":"https://github.com/halo090770/bert"},{"title":"llx666/git_demo","url":"https://github.com/llx666/git_demo"},{"title":"chalothon/BERT_Practice","url":"https://github.com/chalothon/BERT_Practice"},{"title":"ps2811/Bert-Multi-Label-Text-Classification-GitVersion","url":"https://github.com/ps2811/Bert-Multi-Label-Text-Classification-GitVersion"},{"title":"SCismycat/bert_code_view","url":"https://github.com/SCismycat/bert_code_view"},{"title":"karenacorn99/explore-bert","url":"https://github.com/karenacorn99/explore-bert"},{"title":"uabinf/nlp-fall-2019-project-shuhui_shuqu","url":"https://github.com/uabinf/nlp-fall-2019-project-shuhui_shuqu"},{"title":"knuddy/op_text","url":"https://github.com/knuddy/op_text"},{"title":"jinzhenfan/BERT","url":"https://github.com/jinzhenfan/BERT"},{"title":"Nimesh-Patel/BERT","url":"https://github.com/Nimesh-Patel/BERT"},{"title":"knuddj1/op_text","url":"https://github.com/knuddj1/op_text"},{"title":"FaskyCC/TextClassification","url":"https://github.com/FaskyCC/TextClassification"},{"title":"tvinith/bert","url":"https://github.com/tvinith/bert"},{"title":"nachiketaa/bert","url":"https://github.com/nachiketaa/bert"},{"title":"nachiketaa/BERT-pytorch","url":"https://github.com/nachiketaa/BERT-pytorch"},{"title":"Dongcf/Pytorch_Bert_Text_Classification","url":"https://github.com/Dongcf/Pytorch_Bert_Text_Classification"},{"title":"rickyHong/Google-BERT-repl","url":"https://github.com/rickyHong/Google-BERT-repl"},{"title":"EthanWYB/bert-classification","url":"https://github.com/EthanWYB/bert-classification"},{"title":"DataScienceNigeria/Supervised-NLP-from-Facebook-AI-Team","url":"https://github.com/DataScienceNigeria/Supervised-NLP-from-Facebook-AI-Team"},{"title":"maxudong1993/mybert","url":"https://github.com/maxudong1993/mybert"},{"title":"liuqiangict/lamb_optimizer","url":"https://github.com/liuqiangict/lamb_optimizer"},{"title":"YuehChuan/bert-Agus","url":"https://github.com/YuehChuan/bert-Agus"},{"title":"idiotprofessorchen/bert.github.io","url":"https://github.com/idiotprofessorchen/bert.github.io"},{"title":"TonyX19/bert_hyperpartisan","url":"https://github.com/TonyX19/bert_hyperpartisan"},{"title":"Walter-B/bert-20-classes","url":"https://github.com/Walter-B/bert-20-classes"},{"title":"yangyucheng000/bert_GPU","url":"https://github.com/yangyucheng000/bert_GPU"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/bert"},{"title":"yangyucheng000/bert_Ascend","url":"https://github.com/yangyucheng000/bert_Ascend"},{"title":"kingcong/gpu_albert","url":"https://github.com/kingcong/gpu_albert"},{"title":"MindSpore-paper-code-3/code9","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/soft_masked_bert"},{"title":"yangyucheng000/ascend_albert","url":"https://github.com/yangyucheng000/ascend_albert"},{"title":"Osobarako/alduswarrensewell","url":"https://github.com/Osobarako/alduswarrensewell"},{"title":"Gaozhen0816/BERT_QA_for_Chinese","url":"https://github.com/Gaozhen0816/BERT_QA_for_Chinese"},{"title":"zhang-huihui/git-repository","url":"https://github.com/zhang-huihui/git-repository"},{"title":"Soren-Kierkegaard/BERT-for-tweet-Classifcation","url":"https://github.com/Soren-Kierkegaard/BERT-for-tweet-Classifcation"},{"title":"eunseo1092/Graduation_project","url":"https://github.com/eunseo1092/Graduation_project"},{"title":"aleksac99/SQuAD-SR","url":"https://github.com/aleksac99/SQuAD-SR"},{"title":"luozhilin99/bert","url":"https://github.com/luozhilin99/bert"},{"title":"2023-MindSpore-1/ms-code-12","url":"https://github.com/2023-MindSpore-1/ms-code-12"},{"title":"2023-MindSpore-1/ms-code-11","url":"https://github.com/2023-MindSpore-1/ms-code-11"},{"title":"2023-MindSpore-1/ms-code-56","url":"https://github.com/2023-MindSpore-1/ms-code-56"},{"title":"TannerFry/CS522-Final-Project","url":"https://github.com/TannerFry/CS522-Final-Project"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/bert"},{"title":"svakulenk0/response_eval","url":"https://github.com/svakulenk0/response_eval"},{"title":"zsweet/BERT_zsw","url":"https://github.com/zsweet/BERT_zsw"},{"title":"lovedavidsilva/bert_old_version","url":"https://github.com/lovedavidsilva/bert_old_version"},{"title":"myamamoto555/tf-bert","url":"https://github.com/myamamoto555/tf-bert"},{"title":"longbowking/bert","url":"https://github.com/longbowking/bert"},{"title":"semal/bert","url":"https://github.com/semal/bert"},{"title":"Gaozhen0816/BERT_QA_For_AILaw","url":"https://github.com/Gaozhen0816/BERT_QA_For_AILaw"},{"title":"icewing1996/bert_dep","url":"https://github.com/icewing1996/bert_dep"},{"title":"NehaTamore/TextSimilarity","url":"https://github.com/NehaTamore/TextSimilarity"},{"title":"saurabhnlp/bert","url":"https://github.com/saurabhnlp/bert"},{"title":"kinimod23/NMT_Project","url":"https://github.com/kinimod23/NMT_Project"},{"title":"fciannel/bert_fciannel","url":"https://github.com/fciannel/bert_fciannel"},{"title":"TSLNIHAOGIT/bert_run","url":"https://github.com/TSLNIHAOGIT/bert_run"},{"title":"goldenbili/Bert_Test2","url":"https://github.com/goldenbili/Bert_Test2"},{"title":"jangjoongkeon/JK","url":"https://github.com/jangjoongkeon/JK"},{"title":"JohannLee1996/bert","url":"https://github.com/JohannLee1996/bert"},{"title":"kingcheng2000/bert","url":"https://github.com/kingcheng2000/bert"},{"title":"zapplea/bert","url":"https://github.com/zapplea/bert"},{"title":"roshaan7zafar/-MAX-Text-Sentiment-Classifier","url":"https://github.com/roshaan7zafar/-MAX-Text-Sentiment-Classifier"},{"title":"2023-MindSpore-1/ms-code-150","url":"https://github.com/2023-MindSpore-1/ms-code-150"},{"title":"bhavitvyamalik/bert","url":"https://github.com/bhavitvyamalik/bert"},{"title":"g-eklund/bert_tutorial","url":"https://github.com/g-eklund/bert_tutorial"},{"title":"habibullah-araphat/BERT-GPU","url":"https://github.com/habibullah-araphat/BERT-GPU"},{"title":"thanhlong1997/bert_quora","url":"https://github.com/thanhlong1997/bert_quora"},{"title":"TSLNIHAOGIT/bert","url":"https://github.com/TSLNIHAOGIT/bert"},{"title":"YYGXjpg/BERT_WL","url":"https://github.com/YYGXjpg/BERT_WL"},{"title":"haydlite/sparse-bert-ner","url":"https://github.com/haydlite/sparse-bert-ner"},{"title":"faizansuhail89/bert","url":"https://github.com/faizansuhail89/bert"},{"title":"Sikun/dlam_project","url":"https://github.com/Sikun/dlam_project"},{"title":"DeokO/bert-excercise-ongoing","url":"https://github.com/DeokO/bert-excercise-ongoing"},{"title":"yydai/bert_test","url":"https://github.com/yydai/bert_test"},{"title":"enod/arxiv-nlp-notes","url":"https://github.com/enod/arxiv-nlp-notes"},{"title":"tyxr/bert","url":"https://github.com/tyxr/bert"},{"title":"pengshuyuan/Bert","url":"https://github.com/pengshuyuan/Bert"},{"title":"TYTYTYTYTYTYTYTYTY/558-project","url":"https://github.com/TYTYTYTYTYTYTYTYTY/558-project"},{"title":"vijay120/bert","url":"https://github.com/vijay120/bert"},{"title":"Kevin-Vora/bert-embedding-gluonnlp-edit-","url":"https://github.com/Kevin-Vora/bert-embedding-gluonnlp-edit-"},{"title":"xesdiny/test-bert-master","url":"https://github.com/xesdiny/test-bert-master"},{"title":"tcnguyen/bert","url":"https://github.com/tcnguyen/bert"},{"title":"rpuiggari/bert2","url":"https://github.com/rpuiggari/bert2"},{"title":"bluejurand/Kaggle_QA_Google_Labeling","url":"https://github.com/bluejurand/Kaggle_QA_Google_Labeling"},{"title":"Mind23-2/MindCode-133","url":"https://github.com/Mind23-2/MindCode-133"},{"title":"yiyc-kor/bert-study","url":"https://github.com/yiyc-kor/bert-study"},{"title":"coronazap/bert_client","url":"https://github.com/coronazap/bert_client"},{"title":"Mind23-2/MindCode-144","url":"https://github.com/Mind23-2/MindCode-144"},{"title":"saurabhkulkarni77/BERT_multilabel","url":"https://github.com/saurabhkulkarni77/BERT_multilabel"},{"title":"junhahyung/bert_transfer","url":"https://github.com/junhahyung/bert_transfer"},{"title":"Maz101/pretrainingdataset","url":"https://github.com/Maz101/pretrainingdataset"},{"title":"Shinya-Kouda/kgc","url":"https://github.com/Shinya-Kouda/kgc"},{"title":"algharak/BERTenhance","url":"https://github.com/algharak/BERTenhance"},{"title":"FengJiaChunFromSYSU/Bert","url":"https://github.com/FengJiaChunFromSYSU/Bert"},{"title":"Priyanshiguptaaa/CoLA_Sentence_Classification_BERT","url":"https://github.com/Priyanshiguptaaa/CoLA_Sentence_Classification_BERT"},{"title":"owainwest/uniprot_bert","url":"https://github.com/owainwest/uniprot_bert"},{"title":"Linar23/Research_work","url":"https://github.com/Linar23/Research_work"},{"title":"Maz101/Bert","url":"https://github.com/Maz101/Bert"},{"title":"abmitra84/Language_Modeling","url":"https://github.com/abmitra84/Language_Modeling"},{"title":"xitianxiaofeixue/BERT","url":"https://github.com/xitianxiaofeixue/BERT"},{"title":"paolanu/BERT_epitope","url":"https://github.com/paolanu/BERT_epitope"},{"title":"cuber2460/bert","url":"https://github.com/cuber2460/bert"},{"title":"Nstats/bert_MRC","url":"https://github.com/Nstats/bert_MRC"},{"title":"DeligientSloth/QQsim","url":"https://github.com/DeligientSloth/QQsim"},{"title":"Caesarzhang/bert-zh","url":"https://github.com/Caesarzhang/bert-zh"},{"title":"joytianya/google_bert","url":"https://github.com/joytianya/google_bert"},{"title":"Yipeng91/text_classifier_pub","url":"https://github.com/Yipeng91/text_classifier_pub"},{"title":"elenalenaelena/machine-learning-viz","url":"https://github.com/elenalenaelena/machine-learning-viz"},{"title":"Charliesgithub20221030/BERT","url":"https://github.com/Charliesgithub20221030/BERT"},{"title":"mhaseeb123/DeepMSim","url":"https://github.com/mhaseeb123/DeepMSim"},{"title":"1wy/bert","url":"https://github.com/1wy/bert"},{"title":"wayalhruhi/gogle_bert","url":"https://github.com/wayalhruhi/gogle_bert"},{"title":"chen-xiong-yi/OwnBERT","url":"https://github.com/chen-xiong-yi/OwnBERT"},{"title":"sherinaseri/bert","url":"https://github.com/sherinaseri/bert"},{"title":"keiyamashita111/aaproject","url":"https://github.com/keiyamashita111/aaproject"},{"title":"TidalPaladin/neural-summarizer","url":"https://github.com/TidalPaladin/neural-summarizer"},{"title":"Satan012/BERT","url":"https://github.com/Satan012/BERT"},{"title":"pfecht/bert-exploration","url":"https://github.com/pfecht/bert-exploration"},{"title":"chrisleunglokhin/Capstone-BERT","url":"https://github.com/chrisleunglokhin/Capstone-BERT"},{"title":"haidershaour/bert","url":"https://github.com/haidershaour/bert"},{"title":"somiltg/bert","url":"https://github.com/somiltg/bert"},{"title":"tmalbonph/tcbert","url":"https://github.com/tmalbonph/tcbert"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43523,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"RoBERTa + SubRegWeigh (K-means)","metrics":{"Accuracy":"94.84"},"paper_url":"https://arxiv.org/abs/2409.06216v2","paper_title":"SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization","paper_date":"2024-09-10","code_links":[{"title":"4ldk/SubRegWeigh","url":"https://github.com/4ldk/SubRegWeigh"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43524,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"SpanBERT","metrics":{"Accuracy":"94.8"},"paper_url":"https://arxiv.org/abs/1907.10529v3","paper_title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","paper_date":"2019-07-24","code_links":[{"title":"facebookresearch/SpanBERT","url":"https://github.com/facebookresearch/SpanBERT"},{"title":"mandarjoshi90/coref","url":"https://github.com/mandarjoshi90/coref"},{"title":"zixinzeng-jennifer/spanbert_trans","url":"https://github.com/zixinzeng-jennifer/spanbert_trans"},{"title":"wooseok-AI/Korean_e2e_CR_BERT","url":"https://github.com/wooseok-AI/Korean_e2e_CR_BERT"},{"title":"amore-upf/masked-coreference","url":"https://github.com/amore-upf/masked-coreference"},{"title":"UnknownGenie/altered-BERT-KPE","url":"https://github.com/UnknownGenie/altered-BERT-KPE"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43525,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"gMLP-large","metrics":{"Accuracy":"94.8"},"paper_url":"https://arxiv.org/abs/2105.08050v2","paper_title":"Pay Attention to MLPs","paper_date":"2021-05-17","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"xmu-xiaoma666/External-Attention-pytorch","url":"https://github.com/xmu-xiaoma666/External-Attention-pytorch"},{"title":"BR-IDL/PaddleViT","url":"https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/gMLP"},{"title":"nlpodyssey/spago","url":"https://github.com/nlpodyssey/spago/blob/main/pkg/ml/nn/gmlp/model.go"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/mlp_family"},{"title":"lucidrains/g-mlp-pytorch","url":"https://github.com/lucidrains/g-mlp-pytorch"},{"title":"lucidrains/FLASH-pytorch","url":"https://github.com/lucidrains/FLASH-pytorch"},{"title":"martinsbruveris/tensorflow-image-models","url":"https://github.com/martinsbruveris/tensorflow-image-models"},{"title":"liuruiyang98/Jittor-MLP","url":"https://github.com/liuruiyang98/Jittor-MLP"},{"title":"radi-cho/gatedtabtransformer","url":"https://github.com/radi-cho/gatedtabtransformer"},{"title":"lucidrains/g-mlp-gpt","url":"https://github.com/lucidrains/g-mlp-gpt"},{"title":"lucidrains/mlp-gpt-jax","url":"https://github.com/lucidrains/mlp-gpt-jax"},{"title":"jaketae/g-mlp","url":"https://github.com/jaketae/g-mlp"},{"title":"antonyvigouret/Pay-Attention-to-MLPs","url":"https://github.com/antonyvigouret/Pay-Attention-to-MLPs"},{"title":"leaderj1001/Bag-of-MLP","url":"https://github.com/leaderj1001/Bag-of-MLP"},{"title":"NydiaAI/g-mlp-tensorflow","url":"https://github.com/NydiaAI/g-mlp-tensorflow"},{"title":"zer0sh0t/artificial_intelligence","url":"https://github.com/zer0sh0t/artificial_intelligence/tree/master/multimodal_models/gmlp"},{"title":"2024-MindSpore-1/Code3","url":"https://github.com/2024-MindSpore-1/Code3/tree/main/gMLP"},{"title":"cvolcy/gmlp-tf","url":"https://github.com/cvolcy/gmlp-tf"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43526,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Q-BERT (Shen et al., 2020)","metrics":{"Accuracy":"94.8"},"paper_url":"https://arxiv.org/abs/1909.05840v2","paper_title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","paper_date":"2019-09-12","code_links":[],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43527,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Q8BERT (Zafrir et al., 2019)","metrics":{"Accuracy":"94.7"},"paper_url":"https://arxiv.org/abs/1910.06188v2","paper_title":"Q8BERT: Quantized 8Bit BERT","paper_date":"2019-10-14","code_links":[{"title":"NervanaSystems/nlp-architect","url":"https://github.com/NervanaSystems/nlp-architect/blob/master/nlp_architect/models/transformers/quantized_bert.py"},{"title":"intellabs/model-compression-research-package","url":"https://github.com/intellabs/model-compression-research-package"},{"title":"huggingface/block_movement_pruning","url":"https://github.com/huggingface/block_movement_pruning"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/q8bert"},{"title":"iabd/QuantizedNMT","url":"https://github.com/iabd/QuantizedNMT"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43528,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"CNN Large","metrics":{"Accuracy":"94.6"},"paper_url":"http://arxiv.org/abs/1903.07785v1","paper_title":"Cloze-driven Pretraining of Self-attention Networks","paper_date":"2019-03-19","code_links":[],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43529,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"BigBird","metrics":{"Accuracy":"94.6"},"paper_url":"https://arxiv.org/abs/2007.14062v2","paper_title":"Big Bird: Transformers for Longer Sequences","paper_date":"2020-07-28","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/nlp/projects/bigbird"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/bigbird"},{"title":"facebookresearch/xformers","url":"https://github.com/facebookresearch/xformers"},{"title":"google-research/bigbird","url":"https://github.com/google-research/bigbird"},{"title":"monologg/kobigbird","url":"https://github.com/monologg/kobigbird"},{"title":"mim-solutions/bert_for_longer_texts","url":"https://github.com/mim-solutions/bert_for_longer_texts"},{"title":"mim-solutions/roberta_for_longer_texts","url":"https://github.com/mim-solutions/roberta_for_longer_texts"},{"title":"sajjjadayobi/ParsBigBird","url":"https://github.com/sajjjadayobi/ParsBigBird"},{"title":"thefonseca/factorsum","url":"https://github.com/thefonseca/factorsum"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/big_bird"},{"title":"sergeykramp/mthesis-bigbird-embeddings","url":"https://github.com/sergeykramp/mthesis-bigbird-embeddings"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/big_bird"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/bigbird_pegasus"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43530,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"MLM+ del-word+ reorder","metrics":{"Accuracy":"94.5"},"paper_url":"https://arxiv.org/abs/2012.15466v1","paper_title":"CLEAR: Contrastive Learning for Sentence Representation","paper_date":"2020-12-31","code_links":[],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43531,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"ASA + BERT-base","metrics":{"Accuracy":"94.1"},"paper_url":"https://arxiv.org/abs/2206.12608v3","paper_title":"Adversarial Self-Attention for Language Understanding","paper_date":"2022-06-25","code_links":[{"title":"gingasan/adversarialsa","url":"https://github.com/gingasan/adversarialsa"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43532,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"RealFormer","metrics":{"Accuracy":"94.04"},"paper_url":"https://arxiv.org/abs/2012.11747v3","paper_title":"RealFormer: Transformer Likes Residual Attention","paper_date":"2020-12-21","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research"},{"title":"cloneofsimo/RealFormer-pytorch","url":"https://github.com/cloneofsimo/RealFormer-pytorch"},{"title":"jaketae/realformer","url":"https://github.com/jaketae/realformer"},{"title":"JunnYu/x-transformers-paddle","url":"https://github.com/JunnYu/x-transformers-paddle"},{"title":"aivolcano/BERT_MRC_CLS","url":"https://github.com/aivolcano/BERT_MRC_CLS"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43533,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"FNet-Large","metrics":{"Accuracy":"94"},"paper_url":"https://arxiv.org/abs/2105.03824v4","paper_title":"FNet: Mixing Tokens with Fourier Transforms","paper_date":"2021-05-09","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"google-research/google-research","url":"https://github.com/google-research/google-research"},{"title":"facebookresearch/xformers","url":"https://github.com/facebookresearch/xformers"},{"title":"erksch/fnet-pytorch","url":"https://github.com/erksch/fnet-pytorch"},{"title":"jaketae/fnet","url":"https://github.com/jaketae/fnet"},{"title":"HJHGJGHHG/Paddle-FNet","url":"https://github.com/HJHGJGHHG/Paddle-FNet"},{"title":"vineet54/fnet-google-pytorch","url":"https://github.com/vineet54/fnet-google-pytorch"},{"title":"abdelghanibelgaid/FNet-TensorFlow-PyTorch","url":"https://github.com/abdelghanibelgaid/FNet-TensorFlow-PyTorch"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/fnet"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/fnet"},{"title":"amoramine/FNet_with_BART_classification","url":"https://github.com/amoramine/FNet_with_BART_classification"},{"title":"amoramine/FNet_classification","url":"https://github.com/amoramine/FNet_classification"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43534,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"MT-DNN","metrics":{"Accuracy":"93.6"},"paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","paper_date":"2019-11-08","code_links":[{"title":"namisan/mt-dnn","url":"https://github.com/namisan/mt-dnn"},{"title":"microsoft/MT-DNN","url":"https://github.com/microsoft/MT-DNN"},{"title":"archinetai/smart-pytorch","url":"https://github.com/archinetai/smart-pytorch"},{"title":"archinetai/vat-pytorch","url":"https://github.com/archinetai/vat-pytorch"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"},{"title":"chunhuililili/mt_dnn","url":"https://github.com/chunhuililili/mt_dnn"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43535,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"ERNIE","metrics":{"Accuracy":"93.5"},"paper_url":"https://arxiv.org/abs/1905.07129v3","paper_title":"ERNIE: Enhanced Language Representation with Informative Entities","paper_date":"2019-05-17","code_links":[{"title":"thunlp/ERNIE","url":"https://github.com/thunlp/ERNIE"},{"title":"Mind23-2/MindCode-136","url":"https://github.com/Mind23-2/MindCode-136"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43536,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Block-sparse LSTM","metrics":{"Accuracy":"93.2"},"paper_url":"https://blog.openai.com/block-sparse-gpu-kernels/","paper_title":"GPU Kernels for Block-Sparse Weights","paper_date":"2017-12-01","code_links":[{"title":"openai/blocksparse","url":"https://github.com/openai/blocksparse"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43537,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"LM-CPPF RoBERTa-base","metrics":{"Accuracy":"93.2"},"paper_url":"https://arxiv.org/abs/2305.18169v3","paper_title":"LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning","paper_date":"2023-05-29","code_links":[{"title":"amirabaskohi/lm-cppf","url":"https://github.com/amirabaskohi/lm-cppf"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43538,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"TinyBERT-6 67M","metrics":{"Accuracy":"93.1"},"paper_url":"https://arxiv.org/abs/1909.10351v5","paper_title":"TinyBERT: Distilling BERT for Natural Language Understanding","paper_date":"2019-09-23","code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/tinybert"},{"title":"huawei-noah/Pretrained-Language-Model","url":"https://github.com/huawei-noah/Pretrained-Language-Model/tree/master/TinyBERT"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/tinybert"},{"title":"mkavim/finetune_bert","url":"https://github.com/mkavim/finetune_bert"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/tinybert"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/tinybert"},{"title":"xiaolilaoli/tiny_bert_ms","url":"https://github.com/xiaolilaoli/tiny_bert_ms"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/tinybert"},{"title":"graison-thomas/TinyFinBERT","url":"https://github.com/graison-thomas/TinyFinBERT"},{"title":"2023-MindSpore-1/ms-code-166","url":"https://github.com/2023-MindSpore-1/ms-code-166"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43539,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"24hBERT","metrics":{"Accuracy":"93.0"},"paper_url":"https://arxiv.org/abs/2104.07705v2","paper_title":"How to Train BERT with an Academic Budget","paper_date":"2021-04-15","code_links":[{"title":"peteriz/academic-budget-bert","url":"https://github.com/peteriz/academic-budget-bert"},{"title":"IntelLabs/academic-budget-bert","url":"https://github.com/IntelLabs/academic-budget-bert"},{"title":"octanove/shiba","url":"https://github.com/octanove/shiba"},{"title":"yxzwang/normalized-information-payload","url":"https://github.com/yxzwang/normalized-information-payload"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43540,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"SMART+BERT-BASE","metrics":{"Accuracy":"93"},"paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","paper_date":"2019-11-08","code_links":[{"title":"namisan/mt-dnn","url":"https://github.com/namisan/mt-dnn"},{"title":"microsoft/MT-DNN","url":"https://github.com/microsoft/MT-DNN"},{"title":"archinetai/smart-pytorch","url":"https://github.com/archinetai/smart-pytorch"},{"title":"archinetai/vat-pytorch","url":"https://github.com/archinetai/vat-pytorch"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"},{"title":"chunhuililili/mt_dnn","url":"https://github.com/chunhuililili/mt_dnn"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43541,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"TinyBERT-4 14.5M","metrics":{"Accuracy":"92.6"},"paper_url":"https://arxiv.org/abs/1909.10351v5","paper_title":"TinyBERT: Distilling BERT for Natural Language Understanding","paper_date":"2019-09-23","code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/tinybert"},{"title":"huawei-noah/Pretrained-Language-Model","url":"https://github.com/huawei-noah/Pretrained-Language-Model/tree/master/TinyBERT"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/tinybert"},{"title":"mkavim/finetune_bert","url":"https://github.com/mkavim/finetune_bert"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/tinybert"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/tinybert"},{"title":"xiaolilaoli/tiny_bert_ms","url":"https://github.com/xiaolilaoli/tiny_bert_ms"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/tinybert"},{"title":"graison-thomas/TinyFinBERT","url":"https://github.com/graison-thomas/TinyFinBERT"},{"title":"2023-MindSpore-1/ms-code-166","url":"https://github.com/2023-MindSpore-1/ms-code-166"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43542,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"bmLSTM","metrics":{"Accuracy":"91.8"},"paper_url":"http://arxiv.org/abs/1704.01444v2","paper_title":"Learning to Generate Reviews and Discovering Sentiment","paper_date":"2017-04-05","code_links":[{"title":"openai/generating-reviews-discovering-sentiment","url":"https://github.com/openai/generating-reviews-discovering-sentiment"},{"title":"faramarzmunshi/d2l-nlp","url":"https://github.com/faramarzmunshi/d2l-nlp"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43543,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"T5-Small","metrics":{"Accuracy":"91.8"},"paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","paper_date":"2019-10-23","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/t5"},{"title":"google-research/text-to-text-transfer-transformer","url":"https://github.com/google-research/text-to-text-transfer-transformer"},{"title":"amazon-science/chronos-forecasting","url":"https://github.com/amazon-science/chronos-forecasting"},{"title":"google-research/t5x","url":"https://github.com/google-research/t5x"},{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"thudm/swissarmytransformer","url":"https://github.com/thudm/swissarmytransformer"},{"title":"Ki6an/fastT5","url":"https://github.com/Ki6an/fastT5"},{"title":"google/seqio","url":"https://github.com/google/seqio"},{"title":"facebookresearch/atlas","url":"https://github.com/facebookresearch/atlas"},{"title":"conceptofmind/LaMDA-pytorch","url":"https://github.com/conceptofmind/LaMDA-pytorch"},{"title":"conceptofmind/lamda-rlhf-pytorch","url":"https://github.com/conceptofmind/lamda-rlhf-pytorch"},{"title":"thu-keg/omnievent","url":"https://github.com/thu-keg/omnievent"},{"title":"asahi417/lm-question-generation","url":"https://github.com/asahi417/lm-question-generation"},{"title":"abelriboulot/onnxt5","url":"https://github.com/abelriboulot/onnxt5"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"airc-keti/ke-t5","url":"https://github.com/airc-keti/ke-t5"},{"title":"yizhongw/tk-instruct","url":"https://github.com/yizhongw/tk-instruct"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"gulucaptain/dynamictrl","url":"https://github.com/gulucaptain/dynamictrl"},{"title":"google-research/t5x_retrieval","url":"https://github.com/google-research/t5x_retrieval"},{"title":"bigscience-workshop/architecture-objective","url":"https://github.com/bigscience-workshop/architecture-objective"},{"title":"dawn0815/UniSA","url":"https://github.com/dawn0815/UniSA"},{"title":"ibm/graph_ensemble_learning","url":"https://github.com/ibm/graph_ensemble_learning"},{"title":"wangcongcong123/ttt","url":"https://github.com/wangcongcong123/ttt"},{"title":"safakkbilici/Academic-Paper-Title-Recommendation","url":"https://github.com/safakkbilici/Academic-Paper-Title-Recommendation"},{"title":"bayer-science-for-a-better-life/data2text-bioleaflets","url":"https://github.com/bayer-science-for-a-better-life/data2text-bioleaflets"},{"title":"allenai/c4-documentation","url":"https://github.com/allenai/c4-documentation"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"lesterpjy/numeric-t5","url":"https://github.com/lesterpjy/numeric-t5"},{"title":"zhiqic/chartreader","url":"https://github.com/zhiqic/chartreader"},{"title":"LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer","url":"https://github.com/LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer"},{"title":"s-nlp/russe_detox_2022","url":"https://github.com/s-nlp/russe_detox_2022"},{"title":"skoltech-nlp/russe_detox_2022","url":"https://github.com/skoltech-nlp/russe_detox_2022"},{"title":"jongwooko/nash-pruning-official","url":"https://github.com/jongwooko/nash-pruning-official"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/t5"},{"title":"luomancs/retriever_reader_for_okvqa","url":"https://github.com/luomancs/retriever_reader_for_okvqa"},{"title":"qipengguo/p2_webnlg2020","url":"https://github.com/qipengguo/p2_webnlg2020"},{"title":"JunnYu/x-transformers-paddle","url":"https://github.com/JunnYu/x-transformers-paddle"},{"title":"Sharif-SLPL/t5-fa","url":"https://github.com/Sharif-SLPL/t5-fa"},{"title":"shivamraval98/multitask-t5_ae","url":"https://github.com/shivamraval98/multitask-t5_ae"},{"title":"junnyu/paddle_t5","url":"https://github.com/junnyu/paddle_t5"},{"title":"ChernovAndrey/chronos-forecasting-wasserstein","url":"https://github.com/ChernovAndrey/chronos-forecasting-wasserstein"},{"title":"cccntu/ft5-demo","url":"https://github.com/cccntu/ft5-demo"},{"title":"ArvinZhuang/BiTAG","url":"https://github.com/ArvinZhuang/BiTAG"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/t5"},{"title":"cccntu/ft5-demo-space","url":"https://github.com/cccntu/ft5-demo-space"},{"title":"xuetianci/pacit","url":"https://github.com/xuetianci/pacit"},{"title":"vgaraujov/seq2seq-spanish-plms","url":"https://github.com/vgaraujov/seq2seq-spanish-plms"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"thecodemasterk/Text-to-Text-transfer-transformers","url":"https://github.com/thecodemasterk/Text-to-Text-transfer-transformers"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/t5"},{"title":"KAGUYAHONGLAI/SRC","url":"https://github.com/KAGUYAHONGLAI/SRC"},{"title":"Nimesh-Patel/text-to-text-transfer-transformer","url":"https://github.com/Nimesh-Patel/text-to-text-transfer-transformer"},{"title":"souvikshanku/translit-former","url":"https://github.com/souvikshanku/translit-former"},{"title":"itzprashu1/prashant","url":"https://github.com/itzprashu1/prashant"},{"title":"2023-MindSpore-1/ms-code-164","url":"https://github.com/2023-MindSpore-1/ms-code-164"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43544,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"byte mLSTM7","metrics":{"Accuracy":"91.7"},"paper_url":"http://arxiv.org/abs/1805.05388v1","paper_title":"A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors","paper_date":"2018-05-14","code_links":[{"title":"NLPrinceton/ALaCarte","url":"https://github.com/NLPrinceton/ALaCarte"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43545,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"PAR BERT Base","metrics":{"Accuracy":"91.6"},"paper_url":"https://arxiv.org/abs/2009.04534v3","paper_title":"Pay Attention when Required","paper_date":"2020-09-09","code_links":[{"title":"NVIDIA/DeepLearningExamples","url":"https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/LanguageModeling"},{"title":"Jmkernes/PAR-Transformer-XL","url":"https://github.com/Jmkernes/PAR-Transformer-XL"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43546,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Charformer-Base","metrics":{"Accuracy":"91.6"},"paper_url":"https://arxiv.org/abs/2106.12672v3","paper_title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","paper_date":"2021-06-23","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research"},{"title":"lucidrains/charformer-pytorch","url":"https://github.com/lucidrains/charformer-pytorch"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43547,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"SqueezeBERT","metrics":{"Accuracy":"91.4"},"paper_url":"https://arxiv.org/abs/2006.11316v1","paper_title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","paper_date":"2020-06-19","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers/blob/main/src/transformers/models/squeezebert/modeling_squeezebert.py"},{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers/blob/master/src/transformers/modeling_squeezebert.py"},{"title":"mindspore-courses/d2l-mindspore","url":"https://github.com/mindspore-courses/d2l-mindspore/tree/master/chapter_14_natural_language_processing_pretraining"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/squeezebert"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/squeezebert"},{"title":"renmada/squeezebert-paddle","url":"https://github.com/renmada/squeezebert-paddle"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43548,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Nyströmformer","metrics":{"Accuracy":"91.4"},"paper_url":"https://arxiv.org/abs/2102.03902v3","paper_title":"Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention","paper_date":"2021-02-07","code_links":[{"title":"facebookresearch/xformers","url":"https://github.com/facebookresearch/xformers"},{"title":"mlpen/Nystromformer","url":"https://github.com/mlpen/Nystromformer"},{"title":"lucidrains/nystrom-attention","url":"https://github.com/lucidrains/nystrom-attention"},{"title":"Rishit-dagli/Nystromformer","url":"https://github.com/Rishit-dagli/Nystromformer"},{"title":"yxzwang/normalized-information-payload","url":"https://github.com/yxzwang/normalized-information-payload"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/nystromformer"},{"title":"JeremyZhao1998/Nystromformer-Paddle","url":"https://github.com/JeremyZhao1998/Nystromformer-Paddle"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/nystromformer"},{"title":"MindSpore-scientific-2/code-10","url":"https://github.com/MindSpore-scientific-2/code-10/tree/main/nystrom-attention"},{"title":"nellish123/contrib","url":"https://github.com/nellish123/contrib"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43549,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Bi-CAS-LSTM","metrics":{"Accuracy":"91.3"},"paper_url":"https://arxiv.org/abs/1809.02279v2","paper_title":"Cell-aware Stacked LSTMs for Modeling Sentences","paper_date":"2018-09-07","code_links":[],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43550,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"DistilBERT 66M","metrics":{"Accuracy":"91.3"},"paper_url":"https://arxiv.org/abs/1910.01108v4","paper_title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","paper_date":"2019-10-02","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/blob/develop/paddlenlp/transformers/distilbert/modeling.py"},{"title":"huggingface/swift-coreml-transformers","url":"https://github.com/huggingface/swift-coreml-transformers"},{"title":"huggingface/node-question-answering","url":"https://github.com/huggingface/node-question-answering"},{"title":"huggingface/tflite-android-transformers","url":"https://github.com/huggingface/tflite-android-transformers"},{"title":"allenai/scifact","url":"https://github.com/allenai/scifact"},{"title":"monologg/distilkobert","url":"https://github.com/monologg/distilkobert"},{"title":"suinleelab/path_explain","url":"https://github.com/suinleelab/path_explain"},{"title":"epfml/collaborative-attention","url":"https://github.com/epfml/collaborative-attention"},{"title":"sdadas/polish-roberta","url":"https://github.com/sdadas/polish-roberta"},{"title":"jaketae/pytorch-malware-detection","url":"https://github.com/jaketae/pytorch-malware-detection"},{"title":"philschmid/knowledge-distillation-transformers-pytorch-sagemaker","url":"https://github.com/philschmid/knowledge-distillation-transformers-pytorch-sagemaker"},{"title":"Karthik-Bhaskar/Context-Based-Question-Answering","url":"https://github.com/Karthik-Bhaskar/Context-Based-Question-Answering"},{"title":"stefan-it/europeana-bert","url":"https://github.com/stefan-it/europeana-bert"},{"title":"facebookresearch/EgoTV","url":"https://github.com/facebookresearch/EgoTV"},{"title":"frankaging/Causal-Distill","url":"https://github.com/frankaging/Causal-Distill"},{"title":"mkavim/finetune_bert","url":"https://github.com/mkavim/finetune_bert"},{"title":"askaydevs/distillbert-qa","url":"https://github.com/askaydevs/distillbert-qa"},{"title":"semantic-web-company/ptlm_wsid","url":"https://github.com/semantic-web-company/ptlm_wsid"},{"title":"ayeffkay/rubert-tiny","url":"https://github.com/ayeffkay/rubert-tiny"},{"title":"enzomuschik/distilfnd","url":"https://github.com/enzomuschik/distilfnd"},{"title":"tchebonenko/Automated-Topic_Modeling-and-NER","url":"https://github.com/tchebonenko/Automated-Topic_Modeling-and-NER"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/distilbert"},{"title":"nageshsinghc4/deepwrap","url":"https://github.com/nageshsinghc4/deepwrap"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/distilbert"},{"title":"MindSpore-paper-code-2/code399","url":"https://github.com/MindSpore-paper-code-2/code399/tree/main/Bert"},{"title":"Milan-Chicago/GLG-Automated-Meta-data-Tagging","url":"https://github.com/Milan-Chicago/GLG-Automated-Meta-data-Tagging"},{"title":"msorkhpar/wiki-entity-summarization-preprocessor","url":"https://github.com/msorkhpar/wiki-entity-summarization-preprocessor"},{"title":"reycn/multi-modal-scale","url":"https://github.com/reycn/multi-modal-scale"},{"title":"franknb/Text-Summarization","url":"https://github.com/franknb/Text-Summarization"},{"title":"flexible-fl/flex-nlp","url":"https://github.com/flexible-fl/flex-nlp"},{"title":"rybread1/stack-overflow-question-classification","url":"https://github.com/rybread1/stack-overflow-question-classification"},{"title":"knuddy/op_text","url":"https://github.com/knuddy/op_text"},{"title":"lukexyz/Deep-Lyrical-Genius","url":"https://github.com/lukexyz/Deep-Lyrical-Genius"},{"title":"twobooks/intro-aws-training","url":"https://github.com/twobooks/intro-aws-training"},{"title":"knuddj1/op_text","url":"https://github.com/knuddj1/op_text"},{"title":"dngback/co-forget-protocol","url":"https://github.com/dngback/co-forget-protocol"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43551,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"CNN","metrics":{"Accuracy":"91.2"},"paper_url":"http://arxiv.org/abs/1707.01780v3","paper_title":"On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis","paper_date":"2017-07-06","code_links":[{"title":"pedrada88/preproc-textclassification","url":"https://github.com/pedrada88/preproc-textclassification"},{"title":"changji2069/Scope-Project","url":"https://github.com/changji2069/Scope-Project"},{"title":"changji2069/literature-review","url":"https://github.com/changji2069/literature-review"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43552,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Suffix BiLSTM","metrics":{"Accuracy":"91.2"},"paper_url":"http://arxiv.org/abs/1805.07340v2","paper_title":"Improved Sentence Modeling using Suffix Bidirectional LSTM","paper_date":"2018-05-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43553,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"BERT Base","metrics":{"Accuracy":"91.2"},"paper_url":"https://arxiv.org/abs/1910.03474v1","paper_title":"Fine-grained Sentiment Classification using BERT","paper_date":"2019-10-04","code_links":[{"title":"munikarmanish/bert-sentiment","url":"https://github.com/munikarmanish/bert-sentiment"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43554,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Transformer (finetune)","metrics":{"Accuracy":"90.9"},"paper_url":"http://arxiv.org/abs/1812.01207v1","paper_title":"Practical Text Classification With Large Pre-Trained Language Models","paper_date":"2018-12-04","code_links":[{"title":"NVIDIA/sentiment-discovery","url":"https://github.com/NVIDIA/sentiment-discovery"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43555,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Single layer bilstm distilled from BERT","metrics":{"Accuracy":"90.7"},"paper_url":"http://arxiv.org/abs/1903.12136v1","paper_title":"Distilling Task-Specific Knowledge from BERT into Simple Neural Networks","paper_date":"2019-03-28","code_links":[{"title":"pvgladkov/knowledge-distillation","url":"https://github.com/pvgladkov/knowledge-distillation"},{"title":"castorini/d-bert","url":"https://github.com/castorini/d-bert"},{"title":"aqweteddy/BERTDistilForClassification","url":"https://github.com/aqweteddy/BERTDistilForClassification"},{"title":"AI-Mart/distill_lstm","url":"https://github.com/AI-Mart/distill_lstm"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43556,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"BCN+Char+CoVe","metrics":{"Accuracy":"90.3"},"paper_url":"http://arxiv.org/abs/1708.00107v2","paper_title":"Learned in Translation: Contextualized Word Vectors","paper_date":"2017-08-01","code_links":[{"title":"salesforce/cove","url":"https://github.com/salesforce/cove"},{"title":"adi2103/AML-CoVe","url":"https://github.com/adi2103/AML-CoVe"},{"title":"menajosep/AleatoricSent","url":"https://github.com/menajosep/AleatoricSent"},{"title":"richinkabra/CoVe-BCN","url":"https://github.com/richinkabra/CoVe-BCN"},{"title":"cove-adml/adml-anon","url":"https://github.com/cove-adml/adml-anon"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43557,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"CNN-RNF-LSTM","metrics":{"Accuracy":"90.0"},"paper_url":"http://arxiv.org/abs/1808.09315v1","paper_title":"Convolutional Neural Networks with Recurrent Neural Filters","paper_date":"2018-08-28","code_links":[{"title":"bloomberg/cnn-rnf","url":"https://github.com/bloomberg/cnn-rnf"},{"title":"davide97l/Sentiment-analysis","url":"https://github.com/davide97l/Sentiment-analysis"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43558,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Neural Semantic Encoder","metrics":{"Accuracy":"89.7"},"paper_url":"http://arxiv.org/abs/1607.04315v3","paper_title":"Neural Semantic Encoders","paper_date":"2016-07-14","code_links":[{"title":"Smerity/keras_snli","url":"https://github.com/Smerity/keras_snli"},{"title":"tsendeemts/nse","url":"https://bitbucket.org/tsendeemts/nse"},{"title":"saraswat/munkhdalai-nse","url":"https://github.com/saraswat/munkhdalai-nse"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43559,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"BLSTM-2DCNN","metrics":{"Accuracy":"89.5"},"paper_url":"http://arxiv.org/abs/1611.06639v1","paper_title":"Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling","paper_date":"2016-11-21","code_links":[{"title":"ManuelVs/NNForTextClassification","url":"https://github.com/ManuelVs/NNForTextClassification"},{"title":"ManuelVs/NeuralNetworks","url":"https://github.com/ManuelVs/NeuralNetworks"},{"title":"sinhasam/Sentalyze","url":"https://github.com/sinhasam/Sentalyze"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43560,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"CNN + Logic rules","metrics":{"Accuracy":"89.3"},"paper_url":"https://arxiv.org/abs/1603.06318v6","paper_title":"Harnessing Deep Neural Networks with Logic Rules","paper_date":"2016-03-21","code_links":[{"title":"ZhitingHu/logicnn","url":"https://github.com/ZhitingHu/logicnn"},{"title":"martiansideofthemoon/logic-rules-sentiment","url":"https://github.com/martiansideofthemoon/logic-rules-sentiment"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43561,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"DMN [ankit16]","metrics":{"Accuracy":"88.6"},"paper_url":"http://arxiv.org/abs/1506.07285v5","paper_title":"Ask Me Anything: Dynamic Memory Networks for Natural Language Processing","paper_date":"2015-06-24","code_links":[{"title":"DongjunLee/dmn-tensorflow","url":"https://github.com/DongjunLee/dmn-tensorflow"},{"title":"mindspore-courses/DeepNLP-models-MindSpore","url":"https://github.com/mindspore-courses/DeepNLP-models-MindSpore"},{"title":"rgsachin/DMTN","url":"https://github.com/rgsachin/DMTN"},{"title":"vchudinov/dynamic_memory_networks_with_keras","url":"https://github.com/vchudinov/dynamic_memory_networks_with_keras"},{"title":"jxz542189/dmn_plus","url":"https://github.com/jxz542189/dmn_plus"},{"title":"scakc/QAwiki","url":"https://github.com/scakc/QAwiki"},{"title":"ajenningsfrankston/Dynamic-Memory-Network-Plus-master","url":"https://github.com/ajenningsfrankston/Dynamic-Memory-Network-Plus-master"},{"title":"navodhya/DMN","url":"https://github.com/navodhya/DMN"},{"title":"Asteur/someChatbot","url":"https://github.com/Asteur/someChatbot"},{"title":"macco3k/deepstories","url":"https://github.com/macco3k/deepstories"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43562,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"CNN-multichannel [kim2013]","metrics":{"Accuracy":"88.1"},"paper_url":"http://arxiv.org/abs/1408.5882v2","paper_title":"Convolutional Neural Networks for Sentence Classification","paper_date":"2014-08-25","code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/sentiment_analysis/textcnn"},{"title":"facebookresearch/pytext","url":"https://github.com/facebookresearch/pytext"},{"title":"dennybritz/cnn-text-classification-tf","url":"https://github.com/dennybritz/cnn-text-classification-tf"},{"title":"bentrevett/pytorch-sentiment-analysis","url":"https://github.com/bentrevett/pytorch-sentiment-analysis"},{"title":"gaussic/text-classification-cnn-rnn","url":"https://github.com/gaussic/text-classification-cnn-rnn"},{"title":"PaddlePaddle/PaddleRec","url":"https://github.com/PaddlePaddle/PaddleRec/tree/release/2.1.0/models/contentunderstanding/textcnn"},{"title":"dmlc/gluon-nlp","url":"https://github.com/dmlc/gluon-nlp"},{"title":"yoonkim/CNN_sentence","url":"https://github.com/yoonkim/CNN_sentence"},{"title":"TsingZ0/PFL-Non-IID","url":"https://github.com/TsingZ0/PFL-Non-IID"},{"title":"Shawn1993/cnn-text-classification-pytorch","url":"https://github.com/Shawn1993/cnn-text-classification-pytorch"},{"title":"linguishi/chinese_sentiment","url":"https://github.com/linguishi/chinese_sentiment"},{"title":"prakashpandey9/Text-Classification-Pytorch","url":"https://github.com/prakashpandey9/Text-Classification-Pytorch"},{"title":"baiyang2464/chatbot-base-on-Knowledge-Graph","url":"https://github.com/baiyang2464/chatbot-base-on-Knowledge-Graph"},{"title":"TobiasLee/Text-Classification","url":"https://github.com/TobiasLee/Text-Classification"},{"title":"IndicoDataSolutions/finetune","url":"https://github.com/IndicoDataSolutions/finetune"},{"title":"inspirehep/magpie","url":"https://github.com/inspirehep/magpie"},{"title":"alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras","url":"https://github.com/alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras"},{"title":"dongjun-Lee/text-classification-models-tf","url":"https://github.com/dongjun-Lee/text-classification-models-tf"},{"title":"brightmart/ai_law","url":"https://github.com/brightmart/ai_law"},{"title":"DongjunLee/text-cnn-tensorflow","url":"https://github.com/DongjunLee/text-cnn-tensorflow"},{"title":"wiseodd/controlled-text-generation","url":"https://github.com/wiseodd/controlled-text-generation"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/textcnn"},{"title":"shagunsodhani/CNN-Sentence-Classifier","url":"https://github.com/shagunsodhani/CNN-Sentence-Classifier"},{"title":"lvyufeng/mindspore-nlp-tutorial","url":"https://github.com/lvyufeng/mindspore-nlp-tutorial"},{"title":"cmasch/cnn-text-classification","url":"https://github.com/cmasch/cnn-text-classification"},{"title":"radoslawkrolikowski/sentiment-analysis-pytorch","url":"https://github.com/radoslawkrolikowski/sentiment-analysis-pytorch"},{"title":"kh-kim/simple-ntc","url":"https://github.com/kh-kim/simple-ntc"},{"title":"randomrandom/deep-atrous-cnn-sentiment","url":"https://github.com/randomrandom/deep-atrous-cnn-sentiment"},{"title":"timerstime/SDG4DA","url":"https://github.com/timerstime/SDG4DA"},{"title":"delldu/TextCNN","url":"https://github.com/delldu/TextCNN"},{"title":"mindspore-courses/DeepNLP-models-MindSpore","url":"https://github.com/mindspore-courses/DeepNLP-models-MindSpore"},{"title":"yschoi-nisp/AI-Grand-Challenge-2020","url":"https://github.com/yschoi-nisp/AI-Grand-Challenge-2020"},{"title":"bmcclannahan/NLP-Sentiment","url":"https://github.com/bmcclannahan/NLP-Sentiment"},{"title":"threelittlemonkeys/cnn-text-classification-pytorch","url":"https://github.com/threelittlemonkeys/cnn-text-classification-pytorch"},{"title":"threelittlemonkeys/text-cnn-pytorch","url":"https://github.com/threelittlemonkeys/text-cnn-pytorch"},{"title":"yongjincho/cnn-text-classification-pytorch","url":"https://github.com/yongjincho/cnn-text-classification-pytorch"},{"title":"diegoschapira/CNN-Text-Classifier-using-Keras","url":"https://github.com/diegoschapira/CNN-Text-Classifier-using-Keras"},{"title":"HuihuiChyan/BJTUNLP_Practice2020","url":"https://github.com/HuihuiChyan/BJTUNLP_Practice2020"},{"title":"plkumjorn/FIND","url":"https://github.com/plkumjorn/FIND"},{"title":"attardi/CNN_sentence","url":"https://github.com/attardi/CNN_sentence"},{"title":"Jverma/cnn-text-classification-keras","url":"https://github.com/Jverma/cnn-text-classification-keras"},{"title":"wy-ei/Text-CNN","url":"https://github.com/wy-ei/Text-CNN"},{"title":"rachit-shah/News-Classfication-using-DNN-models","url":"https://github.com/rachit-shah/News-Classfication-using-DNN-models"},{"title":"RaffaeleGalliera/pytorch-cnn-text-classification","url":"https://github.com/RaffaeleGalliera/pytorch-cnn-text-classification"},{"title":"frederick0329/text-classification-benchmark","url":"https://github.com/frederick0329/text-classification-benchmark"},{"title":"nestle1993/SE16-Task6-Stance-Detection","url":"https://github.com/nestle1993/SE16-Task6-Stance-Detection"},{"title":"ahmedssabir/textual-visual-semantic-dataset","url":"https://github.com/ahmedssabir/textual-visual-semantic-dataset"},{"title":"HuihuiChyan/BJTUNLP_Practice2021","url":"https://github.com/HuihuiChyan/BJTUNLP_Practice2021"},{"title":"xiaoxinyu1997/Knowledge-Graph","url":"https://github.com/xiaoxinyu1997/Knowledge-Graph"},{"title":"machine-learning-study-group/movie-sentiment-analysis","url":"https://github.com/machine-learning-study-group/movie-sentiment-analysis"},{"title":"toru34/kim_emnlp_2014","url":"https://github.com/toru34/kim_emnlp_2014"},{"title":"lrank/Robust-Representation","url":"https://github.com/lrank/Robust-Representation"},{"title":"Jarvx/text-classification-pytorch","url":"https://github.com/Jarvx/text-classification-pytorch"},{"title":"lrank/Linguistic_adversity","url":"https://github.com/lrank/Linguistic_adversity"},{"title":"au1206/Convolutional-Neural-Networks-for-Sentence-Classification","url":"https://github.com/au1206/Convolutional-Neural-Networks-for-Sentence-Classification"},{"title":"JiachuanDENG/CNN-Textual-RegressionModel-for-commodity-price-prediction","url":"https://github.com/JiachuanDENG/CNN-Textual-RegressionModel-for-commodity-price-prediction"},{"title":"JiachuanDENG/Pytorch-CNN-Textual-RegressionModel-for-commodity-price-prediction","url":"https://github.com/JiachuanDENG/Pytorch-CNN-Textual-RegressionModel-for-commodity-price-prediction"},{"title":"hanfeng108/Language-Detection","url":"https://github.com/hanfeng108/Language-Detection"},{"title":"ahmedbahaaeldin/Papers-from-Scratch","url":"https://github.com/ahmedbahaaeldin/Papers-from-Scratch"},{"title":"pipidog/CNLP","url":"https://github.com/pipidog/CNLP"},{"title":"ManuelVs/NeuralNetworks","url":"https://github.com/ManuelVs/NeuralNetworks"},{"title":"SeonbeomKim/TensorFlow-TextCNN","url":"https://github.com/SeonbeomKim/TensorFlow-TextCNN"},{"title":"bplank/teaching-dl4nlp","url":"https://github.com/bplank/teaching-dl4nlp"},{"title":"ShindongLee/Sentence_Classifier_CNN","url":"https://github.com/ShindongLee/Sentence_Classifier_CNN"},{"title":"MayukhSobo/Conv4RNN","url":"https://github.com/MayukhSobo/Conv4RNN"},{"title":"ManuelVs/NNForTextClassification","url":"https://github.com/ManuelVs/NNForTextClassification"},{"title":"Coda-s/BJTU_NLP_Practice","url":"https://github.com/Coda-s/BJTU_NLP_Practice"},{"title":"adi2103/AML-CoVe","url":"https://github.com/adi2103/AML-CoVe"},{"title":"Johnnylyu/Text-Mining-and-Classification-for-Attain","url":"https://github.com/Johnnylyu/Text-Mining-and-Classification-for-Attain"},{"title":"cjyanyi/CS542-tweets-sentiment-analysis","url":"https://github.com/cjyanyi/CS542-tweets-sentiment-analysis"},{"title":"gmichalo/question_identification_on_medical_logs","url":"https://github.com/gmichalo/question_identification_on_medical_logs"},{"title":"guanliu321/CNN-RNN-HAN-for-Text-Classification-Using-NLP","url":"https://github.com/guanliu321/CNN-RNN-HAN-for-Text-Classification-Using-NLP"},{"title":"adamx97/Data-Science-Advanced-Capstone","url":"https://github.com/adamx97/Data-Science-Advanced-Capstone"},{"title":"nithishkaviyan/Sentiment-Analysis-of-Yelp-Reviews","url":"https://github.com/nithishkaviyan/Sentiment-Analysis-of-Yelp-Reviews"},{"title":"rainorangelemon/TextCNN-with-Attention","url":"https://github.com/rainorangelemon/TextCNN-with-Attention"},{"title":"svjan5/CNN-for-text-classification","url":"https://github.com/svjan5/CNN-for-text-classification"},{"title":"pipidog/QNLP","url":"https://github.com/pipidog/QNLP"},{"title":"avinashsai/Convolutional-Neural-Networks-for-Text-Classification","url":"https://github.com/avinashsai/Convolutional-Neural-Networks-for-Text-Classification"},{"title":"Negus25/MindSpore-CNN_sentence","url":"https://github.com/Negus25/MindSpore-CNN_sentence"},{"title":"fangrouli/Document-embedding-generation-models","url":"https://github.com/fangrouli/Document-embedding-generation-models"},{"title":"reneang17/authorencoder","url":"https://github.com/reneang17/authorencoder"},{"title":"zhouyixin829/Analysis-on-Stop-Asian-Hate-trend-from-Twitter","url":"https://github.com/zhouyixin829/Analysis-on-Stop-Asian-Hate-trend-from-Twitter"},{"title":"yinghao1019/NLP_and_DL_practice","url":"https://github.com/yinghao1019/NLP_and_DL_practice/blob/master/Convolution_Neural_Netowrks_for_sentence_classification_Practice.ipynb"},{"title":"Jerryten/model_nlp","url":"https://github.com/Jerryten/model_nlp"},{"title":"piyush2896/CNN-Text-Classifier","url":"https://github.com/piyush2896/CNN-Text-Classifier"},{"title":"vithyayogarajan/covid-19-patient-shielding","url":"https://github.com/vithyayogarajan/covid-19-patient-shielding"},{"title":"chiemenz/AzureML-Sentiment-Classification-and-Model-Deployment","url":"https://github.com/chiemenz/AzureML-Sentiment-Classification-and-Model-Deployment"},{"title":"chiemenz/automl_vs_hyperdrive","url":"https://github.com/chiemenz/automl_vs_hyperdrive"},{"title":"PJamesY/category_classification-NLP-","url":"https://github.com/PJamesY/category_classification-NLP-"},{"title":"ddajing/multilayer-cnn-text-classification","url":"https://github.com/ddajing/multilayer-cnn-text-classification"},{"title":"yinghao1019/NLP_and_DL_practice","url":"https://github.com/yinghao1019/NLP_and_DL_practice"},{"title":"cove-adml/adml-anon","url":"https://github.com/cove-adml/adml-anon"},{"title":"usama6832/attention_model","url":"https://github.com/usama6832/attention_model"},{"title":"gyanmittal/text-classification-using-char-level-embedding-with-cnn-and-keras","url":"https://github.com/gyanmittal/text-classification-using-char-level-embedding-with-cnn-and-keras"},{"title":"yangyucheng000/textcnn","url":"https://github.com/yangyucheng000/textcnn"},{"title":"MingyuLi19910814/Convolutional-Neural-Networks-for-Sentence-Classification-tf2","url":"https://github.com/MingyuLi19910814/Convolutional-Neural-Networks-for-Sentence-Classification-tf2"},{"title":"hi-underworld/Imformation-Retrieval-weekly-report","url":"https://github.com/hi-underworld/Imformation-Retrieval-weekly-report"},{"title":"pranjalg96/Stylized-Image-captioning","url":"https://github.com/pranjalg96/Stylized-Image-captioning"},{"title":"Kim-inhwan/Word2vec-CNN-for-classfication","url":"https://github.com/Kim-inhwan/Word2vec-CNN-for-classfication"},{"title":"DataZwer/BaseTensorFlowModel","url":"https://github.com/DataZwer/BaseTensorFlowModel"},{"title":"nvshrao/Pytorch-GLUE","url":"https://github.com/nvshrao/Pytorch-GLUE"},{"title":"paper-cat/Sentence-Classifications","url":"https://github.com/paper-cat/Sentence-Classifications"},{"title":"unik00/textCNN-pytorch","url":"https://github.com/unik00/textCNN-pytorch"},{"title":"ryokamoi/cnn_for_sentence_classification","url":"https://github.com/ryokamoi/cnn_for_sentence_classification"},{"title":"audqhsid/-Review-CNN-for-Sentence-Classification","url":"https://github.com/audqhsid/-Review-CNN-for-Sentence-Classification"},{"title":"afrozloya/charrec","url":"https://github.com/afrozloya/charrec"},{"title":"DataZwer/CNNTextClassification","url":"https://github.com/DataZwer/CNNTextClassification"},{"title":"thisisiron/kaggle-toxic-comment","url":"https://github.com/thisisiron/kaggle-toxic-comment"},{"title":"aniketfadia96/Convolutional-Neural-Networks-for-Text-Classification","url":"https://github.com/aniketfadia96/Convolutional-Neural-Networks-for-Text-Classification"},{"title":"andrewfwalters/w266-final-project","url":"https://github.com/andrewfwalters/w266-final-project"},{"title":"kushalj001/Kaggle-Quora-Insincere-Questions-Challenge","url":"https://github.com/kushalj001/Kaggle-Quora-Insincere-Questions-Challenge"},{"title":"rakeshmp18/Text_Analytics","url":"https://github.com/rakeshmp18/Text_Analytics"},{"title":"Nirvanabc/sentence_classification","url":"https://github.com/Nirvanabc/sentence_classification"},{"title":"kshitij1489/review_classification","url":"https://github.com/kshitij1489/review_classification"},{"title":"unik00/textCNN-tf2","url":"https://github.com/unik00/textCNN-tf2"},{"title":"richinkabra/CoVe-BCN","url":"https://github.com/richinkabra/CoVe-BCN"},{"title":"brianyan918/CNN-for-Sentence-Classification","url":"https://github.com/brianyan918/CNN-for-Sentence-Classification"},{"title":"JacobLau0513/676-MBTI","url":"https://github.com/JacobLau0513/676-MBTI"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43563,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Consistency Tree LSTM with tuned Glove vectors [tai2015improved]","metrics":{"Accuracy":"88.0"},"paper_url":"http://arxiv.org/abs/1503.00075v3","paper_title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","paper_date":"2015-02-28","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/tree_lstm"},{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/tree_lstm"},{"title":"tensorflow/fold","url":"https://github.com/tensorflow/fold"},{"title":"stanfordnlp/treelstm","url":"https://github.com/stanfordnlp/treelstm"},{"title":"dasguptar/treelstm.pytorch","url":"https://github.com/dasguptar/treelstm.pytorch"},{"title":"ttpro1995/TreeLSTMSentiment","url":"https://github.com/ttpro1995/TreeLSTMSentiment"},{"title":"inyukwo1/tree-lstm","url":"https://github.com/inyukwo1/tree-lstm"},{"title":"munashe5/SemanticTreeLSTM","url":"https://github.com/munashe5/SemanticTreeLSTM"},{"title":"tomekkorbak/treehopper","url":"https://github.com/tomekkorbak/treehopper"},{"title":"EmilReinert/DeepLearningPipelines","url":"https://github.com/EmilReinert/DeepLearningPipelines"},{"title":"rohitguptacs/ReVal","url":"https://github.com/rohitguptacs/ReVal"},{"title":"vastsak/tree_structured_gru","url":"https://github.com/vastsak/tree_structured_gru"},{"title":"zxk19981227/LSTM-SST","url":"https://github.com/zxk19981227/LSTM-SST"},{"title":"Mind23-2/MindCode-17","url":"https://github.com/Mind23-2/MindCode-17"},{"title":"jayanti-prasad/TreeLSTM","url":"https://github.com/jayanti-prasad/TreeLSTM"},{"title":"Vivswan/Sentiment-Analysis-TreeLSTM","url":"https://github.com/Vivswan/Sentiment-Analysis-TreeLSTM"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43564,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"C-LSTM","metrics":{"Accuracy":"87.8"},"paper_url":"http://arxiv.org/abs/1511.08630v2","paper_title":"A C-LSTM Neural Network for Text Classification","paper_date":"2015-11-27","code_links":[{"title":"zackhy/TextClassification","url":"https://github.com/zackhy/TextClassification"},{"title":"EngSalem/ArabicTextClassification","url":"https://github.com/EngSalem/ArabicTextClassification"},{"title":"EngSalem/TextClassification_Off_the_shelf","url":"https://github.com/EngSalem/TextClassification_Off_the_shelf"},{"title":"EngSalem/Text-Classification-of-the-shelf-with-a-normalizer-for-Arabic-text-","url":"https://github.com/EngSalem/Text-Classification-of-the-shelf-with-a-normalizer-for-Arabic-text-"},{"title":"jingyuanz/telecom_query_classification","url":"https://github.com/jingyuanz/telecom_query_classification"},{"title":"ManuelVs/NeuralNetworks","url":"https://github.com/ManuelVs/NeuralNetworks"},{"title":"KifayatMsd/C-LSTM-text-classification","url":"https://github.com/KifayatMsd/C-LSTM-text-classification"},{"title":"ManuelVs/NNForTextClassification","url":"https://github.com/ManuelVs/NNForTextClassification"},{"title":"MingyuLi19910814/C-LSTM-Tensorflow","url":"https://github.com/MingyuLi19910814/C-LSTM-Tensorflow"},{"title":"shamalwinchurkar/question-classification","url":"https://github.com/shamalwinchurkar/question-classification"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43565,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"MPAD-path","metrics":{"Accuracy":"87.75"},"paper_url":"https://arxiv.org/abs/1908.06267v2","paper_title":"Message Passing Attention Networks for Document Understanding","paper_date":"2019-08-17","code_links":[{"title":"giannisnik/mpad","url":"https://github.com/giannisnik/mpad"},{"title":"Tixierae/gow_tools","url":"https://github.com/Tixierae/gow_tools"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43566,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Standard DR-AGG","metrics":{"Accuracy":"87.6"},"paper_url":"http://arxiv.org/abs/1806.01501v1","paper_title":"Information Aggregation via Dynamic Routing for Sequence Encoding","paper_date":"2018-06-05","code_links":[{"title":"FudanNLP/Capsule4TextClassification","url":"https://github.com/FudanNLP/Capsule4TextClassification"},{"title":"michael-wzhu/dynamic_routing_pytorch","url":"https://github.com/michael-wzhu/dynamic_routing_pytorch"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43567,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"USE_T+CNN (lrn w.e.) ","metrics":{"Accuracy":"87.21"},"paper_url":"http://arxiv.org/abs/1803.11175v2","paper_title":"Universal Sentence Encoder","paper_date":"2018-03-29","code_links":[{"title":"facebookresearch/InferSent","url":"https://github.com/facebookresearch/InferSent"},{"title":"facebookresearch/SentEval","url":"https://github.com/facebookresearch/SentEval"},{"title":"textflint/textflint","url":"https://github.com/textflint/textflint"},{"title":"ncbi-nlp/BioSentVec","url":"https://github.com/ncbi-nlp/BioSentVec"},{"title":"martinomensio/spacy-universal-sentence-encoder","url":"https://github.com/martinomensio/spacy-universal-sentence-encoder"},{"title":"ncbi-nlp/BioWordVec","url":"https://github.com/ncbi-nlp/BioWordVec"},{"title":"ppapalampidi/SUMMER","url":"https://github.com/ppapalampidi/SUMMER"},{"title":"korymath/jann","url":"https://github.com/korymath/jann"},{"title":"ppapalampidi/GraphTP","url":"https://github.com/ppapalampidi/GraphTP"},{"title":"idanmoradarthas/text-summarization","url":"https://github.com/idanmoradarthas/text-summarization"},{"title":"TAUSBV/sentence-level-domain-classification","url":"https://github.com/TAUSBV/sentence-level-domain-classification"},{"title":"asgaardlab/test-case-similarity-technique","url":"https://github.com/asgaardlab/test-case-similarity-technique"},{"title":"weiyezhimeng/silent-guardian","url":"https://github.com/weiyezhimeng/silent-guardian"},{"title":"ceshine/textrank_summary_benchmark","url":"https://github.com/ceshine/textrank_summary_benchmark"},{"title":"contemn1/sentence_embeddings","url":"https://github.com/contemn1/sentence_embeddings"},{"title":"advaithsrao/TwitterSentimentAnalysis_using_UniversalSentenceEncoder","url":"https://github.com/advaithsrao/TwitterSentimentAnalysis_using_UniversalSentenceEncoder"},{"title":"jobdataexchange/competensor","url":"https://github.com/jobdataexchange/competensor"},{"title":"f-data/ADD","url":"https://github.com/f-data/ADD"},{"title":"MirkoLenz/ReCAP-Argument-Graph-Retrieval","url":"https://github.com/MirkoLenz/ReCAP-Argument-Graph-Retrieval"},{"title":"joseph-bongo-220/TV_NLP_Project","url":"https://github.com/joseph-bongo-220/TV_NLP_Project"},{"title":"Alleansa/eluvio","url":"https://github.com/Alleansa/eluvio"},{"title":"pathway/crosslang_embed","url":"https://github.com/pathway/crosslang_embed"},{"title":"ReCAP-UTR/Argument-Graph-Retrieval","url":"https://github.com/ReCAP-UTR/Argument-Graph-Retrieval"},{"title":"krisbukovi/document_similarity","url":"https://github.com/krisbukovi/document_similarity"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43568,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Reverse DR-AGG","metrics":{"Accuracy":"87.2"},"paper_url":"http://arxiv.org/abs/1806.01501v1","paper_title":"Information Aggregation via Dynamic Routing for Sequence Encoding","paper_date":"2018-06-05","code_links":[{"title":"FudanNLP/Capsule4TextClassification","url":"https://github.com/FudanNLP/Capsule4TextClassification"},{"title":"michael-wzhu/dynamic_routing_pytorch","url":"https://github.com/michael-wzhu/dynamic_routing_pytorch"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43569,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"DC-MCNN","metrics":{"Accuracy":"86.99"},"paper_url":"https://aclanthology.org/P18-1235","paper_title":"A Helping Hand: Transfer Learning for Deep Sentiment Analysis","paper_date":"2018-07-01","code_links":[],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43570,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"STM+TSED+PT+2L","metrics":{"Accuracy":"86.95"},"paper_url":"https://arxiv.org/abs/1906.00095v1","paper_title":"The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning","paper_date":"2019-05-31","code_links":[{"title":"bgshin/distill_demo","url":"https://github.com/bgshin/distill_demo"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43571,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Capsule-B ","metrics":{"Accuracy":"86.8"},"paper_url":"http://arxiv.org/abs/1804.00538v4","paper_title":"Investigating Capsule Networks with Dynamic Routing for Text Classification","paper_date":"2018-03-29","code_links":[{"title":"andyweizhao/capsule_text_classification","url":"https://github.com/andyweizhao/capsule_text_classification"},{"title":"andyweizhao/capsule","url":"https://github.com/andyweizhao/capsule"},{"title":"abhishek-924/Capsule-Network","url":"https://github.com/abhishek-924/Capsule-Network"},{"title":"kevindeangeli/capsuleNetwork","url":"https://github.com/kevindeangeli/capsuleNetwork"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43572,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"2-layer LSTM [tai2015improved]","metrics":{"Accuracy":"86.3"},"paper_url":"http://arxiv.org/abs/1503.00075v3","paper_title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","paper_date":"2015-02-28","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/tree_lstm"},{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/tree_lstm"},{"title":"tensorflow/fold","url":"https://github.com/tensorflow/fold"},{"title":"stanfordnlp/treelstm","url":"https://github.com/stanfordnlp/treelstm"},{"title":"dasguptar/treelstm.pytorch","url":"https://github.com/dasguptar/treelstm.pytorch"},{"title":"ttpro1995/TreeLSTMSentiment","url":"https://github.com/ttpro1995/TreeLSTMSentiment"},{"title":"inyukwo1/tree-lstm","url":"https://github.com/inyukwo1/tree-lstm"},{"title":"munashe5/SemanticTreeLSTM","url":"https://github.com/munashe5/SemanticTreeLSTM"},{"title":"tomekkorbak/treehopper","url":"https://github.com/tomekkorbak/treehopper"},{"title":"EmilReinert/DeepLearningPipelines","url":"https://github.com/EmilReinert/DeepLearningPipelines"},{"title":"rohitguptacs/ReVal","url":"https://github.com/rohitguptacs/ReVal"},{"title":"vastsak/tree_structured_gru","url":"https://github.com/vastsak/tree_structured_gru"},{"title":"zxk19981227/LSTM-SST","url":"https://github.com/zxk19981227/LSTM-SST"},{"title":"Mind23-2/MindCode-17","url":"https://github.com/Mind23-2/MindCode-17"},{"title":"jayanti-prasad/TreeLSTM","url":"https://github.com/jayanti-prasad/TreeLSTM"},{"title":"Vivswan/Sentiment-Analysis-TreeLSTM","url":"https://github.com/Vivswan/Sentiment-Analysis-TreeLSTM"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43573,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"SWEM-concat","metrics":{"Accuracy":"84.3"},"paper_url":"http://arxiv.org/abs/1805.09843v1","paper_title":"Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms","paper_date":"2018-05-24","code_links":[{"title":"dinghanshen/SWEM","url":"https://github.com/dinghanshen/SWEM"},{"title":"nyk510/scdv-python","url":"https://github.com/nyk510/scdv-python"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43574,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"MV-RNN","metrics":{"Accuracy":"82.9"},"paper_url":"https://aclanthology.org/D13-1170","paper_title":"Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank","paper_date":"2013-10-01","code_links":[{"title":"stanfordnlp/CoreNLP","url":"https://github.com/stanfordnlp/CoreNLP"},{"title":"mindspore-courses/DeepNLP-models-MindSpore","url":"https://github.com/mindspore-courses/DeepNLP-models-MindSpore"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43575,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"GloVe+Emo2Vec","metrics":{"Accuracy":"82.3"},"paper_url":"http://arxiv.org/abs/1809.04505v1","paper_title":"Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training","paper_date":"2018-09-12","code_links":[{"title":"pxuab/emo2vec_wassa_paper","url":"https://github.com/pxuab/emo2vec_wassa_paper"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43576,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Emo2Vec","metrics":{"Accuracy":"81.2"},"paper_url":"http://arxiv.org/abs/1809.04505v1","paper_title":"Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training","paper_date":"2018-09-12","code_links":[{"title":"pxuab/emo2vec_wassa_paper","url":"https://github.com/pxuab/emo2vec_wassa_paper"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43577,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"ToWE-CBOW","metrics":{"Accuracy":"78.8"},"paper_url":"https://aclanthology.org/C18-1172","paper_title":"Task-oriented Word Embedding for Text Classification","paper_date":"2018-08-01","code_links":[{"title":"qianliu0708/ToWE","url":"https://github.com/qianliu0708/ToWE"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43578,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Joined Model Multi-tasking","metrics":{"Accuracy":" 54.72 "},"paper_url":"https://aclanthology.org/W17-5535","paper_title":"Exploring Joint Neural Model for Sentence Level Discourse Parsing and Sentiment Analysis","paper_date":"2017-08-01","code_links":[],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43579,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"SMARTRoBERTa","metrics":{"Dev Accuracy":"96.9"},"paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","paper_date":"2019-11-08","code_links":[{"title":"namisan/mt-dnn","url":"https://github.com/namisan/mt-dnn"},{"title":"microsoft/MT-DNN","url":"https://github.com/microsoft/MT-DNN"},{"title":"archinetai/smart-pytorch","url":"https://github.com/archinetai/smart-pytorch"},{"title":"archinetai/vat-pytorch","url":"https://github.com/archinetai/vat-pytorch"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"},{"title":"chunhuililili/mt_dnn","url":"https://github.com/chunhuililili/mt_dnn"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43580,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"SMART-MT-DNN","metrics":{"Dev Accuracy":"96.1"},"paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","paper_date":"2019-11-08","code_links":[{"title":"namisan/mt-dnn","url":"https://github.com/namisan/mt-dnn"},{"title":"microsoft/MT-DNN","url":"https://github.com/microsoft/MT-DNN"},{"title":"archinetai/smart-pytorch","url":"https://github.com/archinetai/smart-pytorch"},{"title":"archinetai/vat-pytorch","url":"https://github.com/archinetai/vat-pytorch"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"},{"title":"chunhuililili/mt_dnn","url":"https://github.com/chunhuililili/mt_dnn"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43581,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"SMART-BERT","metrics":{"Dev Accuracy":"93.0"},"paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","paper_date":"2019-11-08","code_links":[{"title":"namisan/mt-dnn","url":"https://github.com/namisan/mt-dnn"},{"title":"microsoft/MT-DNN","url":"https://github.com/microsoft/MT-DNN"},{"title":"archinetai/smart-pytorch","url":"https://github.com/archinetai/smart-pytorch"},{"title":"archinetai/vat-pytorch","url":"https://github.com/archinetai/vat-pytorch"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"},{"title":"chunhuililili/mt_dnn","url":"https://github.com/chunhuililili/mt_dnn"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":43582,"task":"Sentiment Analysis","parent_task":null,"dataset":"SST-2 Binary classification","model_name":"Word+ES (Scratch)","metrics":{"Attack Success Rate":"100"},"paper_url":"https://arxiv.org/abs/2210.09545v1","paper_title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","paper_date":"2022-10-18","code_links":[{"title":"huggingface/pytorch-transformers","url":"https://github.com/huggingface/pytorch-transformers"}],"metrics_order":"[\"Accuracy\", \"Dev Accuracy\", \"Attack Success Rate\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}