{"task":"Coreference Resolution","dataset":"Winograd Schema Challenge","metric_names":["Accuracy"],"rows":[{"id":52383,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"PaLM 540B (fine-tuned)","metrics":{"Accuracy":"100"},"paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","paper_date":"2022-04-05","code_links":[{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"lucidrains/PaLM-pytorch","url":"https://github.com/lucidrains/PaLM-pytorch"},{"title":"google/paxml","url":"https://github.com/google/paxml"},{"title":"foundation-model-stack/fms-fsdp","url":"https://github.com/foundation-model-stack/fms-fsdp"},{"title":"lucidrains/PaLM-jax","url":"https://github.com/lucidrains/PaLM-jax"},{"title":"chrisociepa/allamo","url":"https://github.com/chrisociepa/allamo"},{"title":"conceptofmind/PaLM-flax","url":"https://github.com/conceptofmind/PaLM-flax"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52384,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Vega v2 6B (KD-based prompt transfer)","metrics":{"Accuracy":"98.6"},"paper_url":"https://arxiv.org/abs/2212.01853v1","paper_title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","paper_date":"2022-12-04","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52385,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"UL2 20B (fine-tuned)","metrics":{"Accuracy":"98.1"},"paper_url":"https://arxiv.org/abs/2205.05131v3","paper_title":"UL2: Unifying Language Learning Paradigms","paper_date":"2022-05-10","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research"},{"title":"opennlg/openba-v2","url":"https://github.com/opennlg/openba-v2"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52386,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Turing NLR v5 XXL 5.4B (fine-tuned)","metrics":{"Accuracy":"97.3"},"paper_url":"https://arxiv.org/abs/2212.01853v1","paper_title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","paper_date":"2022-12-04","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52387,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"ST-MoE-32B 269B (fine-tuned)","metrics":{"Accuracy":"96.6"},"paper_url":"https://arxiv.org/abs/2202.08906v2","paper_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","paper_date":"2022-02-17","code_links":[{"title":"tensorflow/mesh","url":"https://github.com/tensorflow/mesh"},{"title":"xuefuzhao/openmoe","url":"https://github.com/xuefuzhao/openmoe"},{"title":"yikangshen/megablocks","url":"https://github.com/yikangshen/megablocks"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52388,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"DeBERTa-1.5B","metrics":{"Accuracy":"95.9"},"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\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52389,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"T5-XXL 11B (fine-tuned)","metrics":{"Accuracy":"93.8"},"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\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52390,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"ST-MoE-L 4.1B (fine-tuned)","metrics":{"Accuracy":"93.3"},"paper_url":"https://arxiv.org/abs/2202.08906v2","paper_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","paper_date":"2022-02-17","code_links":[{"title":"tensorflow/mesh","url":"https://github.com/tensorflow/mesh"},{"title":"xuefuzhao/openmoe","url":"https://github.com/xuefuzhao/openmoe"},{"title":"yikangshen/megablocks","url":"https://github.com/yikangshen/megablocks"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52391,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"RoBERTa-WinoGrande 355M","metrics":{"Accuracy":"90.1"},"paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","paper_date":"2019-07-24","code_links":[{"title":"vered1986/self_talk","url":"https://github.com/vered1986/self_talk"},{"title":"mindspore-ai/contrib","url":"https://github.com/mindspore-ai/contrib/tree/master/application/WinoGrande"},{"title":"swarnahub/explanationhardness","url":"https://github.com/swarnahub/explanationhardness"},{"title":"crherlihy/clinical_nli_artifacts","url":"https://github.com/crherlihy/clinical_nli_artifacts"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/4/WinoGrande"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/3/WinoGrande"},{"title":"MindCode-4/code-13","url":"https://github.com/MindCode-4/code-13/tree/main/WinoGrande"},{"title":"MindSpore-scientific/code-5","url":"https://github.com/MindSpore-scientific/code-5/tree/main/WinoGrande"},{"title":"MindSpore-scientific/code-14","url":"https://github.com/MindSpore-scientific/code-14/tree/main/WinoGrande"},{"title":"MindSpore-scientific-2/code-3","url":"https://github.com/MindSpore-scientific-2/code-3/tree/main/WinoGrande"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52392,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Flan-T5 XXL (zero -shot)","metrics":{"Accuracy":"89.82"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"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":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52393,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"PaLM 540B (5-shot)","metrics":{"Accuracy":"89.5"},"paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","paper_date":"2022-04-05","code_links":[{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"lucidrains/PaLM-pytorch","url":"https://github.com/lucidrains/PaLM-pytorch"},{"title":"google/paxml","url":"https://github.com/google/paxml"},{"title":"foundation-model-stack/fms-fsdp","url":"https://github.com/foundation-model-stack/fms-fsdp"},{"title":"lucidrains/PaLM-jax","url":"https://github.com/lucidrains/PaLM-jax"},{"title":"chrisociepa/allamo","url":"https://github.com/chrisociepa/allamo"},{"title":"conceptofmind/PaLM-flax","url":"https://github.com/conceptofmind/PaLM-flax"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52394,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"PaLM 540B (0-shot)","metrics":{"Accuracy":"89.1"},"paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","paper_date":"2022-04-05","code_links":[{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"lucidrains/PaLM-pytorch","url":"https://github.com/lucidrains/PaLM-pytorch"},{"title":"google/paxml","url":"https://github.com/google/paxml"},{"title":"foundation-model-stack/fms-fsdp","url":"https://github.com/foundation-model-stack/fms-fsdp"},{"title":"lucidrains/PaLM-jax","url":"https://github.com/lucidrains/PaLM-jax"},{"title":"chrisociepa/allamo","url":"https://github.com/chrisociepa/allamo"},{"title":"conceptofmind/PaLM-flax","url":"https://github.com/conceptofmind/PaLM-flax"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52395,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"PaLM 2-M (1-shot)","metrics":{"Accuracy":"88.1"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52396,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"PaLM 2-L (1-shot)","metrics":{"Accuracy":"86.9"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52397,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"FLAN 137B (prompt-tuned)","metrics":{"Accuracy":"86.5"},"paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","paper_date":"2021-09-03","code_links":[{"title":"hiyouga/llama-efficient-tuning","url":"https://github.com/hiyouga/llama-efficient-tuning"},{"title":"bigcode-project/starcoder","url":"https://github.com/bigcode-project/starcoder"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"ukplab/arxiv2025-inherent-limits-plms","url":"https://github.com/ukplab/arxiv2025-inherent-limits-plms"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"MS-P3/code6","url":"https://github.com/MS-P3/code6/tree/main/finetune"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52398,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"PaLM 540B (1-shot)","metrics":{"Accuracy":"86.3"},"paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","paper_date":"2022-04-05","code_links":[{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"lucidrains/PaLM-pytorch","url":"https://github.com/lucidrains/PaLM-pytorch"},{"title":"google/paxml","url":"https://github.com/google/paxml"},{"title":"foundation-model-stack/fms-fsdp","url":"https://github.com/foundation-model-stack/fms-fsdp"},{"title":"lucidrains/PaLM-jax","url":"https://github.com/lucidrains/PaLM-jax"},{"title":"chrisociepa/allamo","url":"https://github.com/chrisociepa/allamo"},{"title":"conceptofmind/PaLM-flax","url":"https://github.com/conceptofmind/PaLM-flax"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52399,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"TTTTT 3B (fine-tuned)","metrics":{"Accuracy":"84.6"},"paper_url":"https://arxiv.org/abs/2003.08380v1","paper_title":"TTTTTackling WinoGrande Schemas","paper_date":"2020-03-18","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52400,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"PaLM 2-S (1-shot)","metrics":{"Accuracy":"84.6"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52401,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"RoBERTa-DPR 355M","metrics":{"Accuracy":"83.1"},"paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","paper_date":"2019-07-24","code_links":[{"title":"vered1986/self_talk","url":"https://github.com/vered1986/self_talk"},{"title":"mindspore-ai/contrib","url":"https://github.com/mindspore-ai/contrib/tree/master/application/WinoGrande"},{"title":"swarnahub/explanationhardness","url":"https://github.com/swarnahub/explanationhardness"},{"title":"crherlihy/clinical_nli_artifacts","url":"https://github.com/crherlihy/clinical_nli_artifacts"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/4/WinoGrande"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/3/WinoGrande"},{"title":"MindCode-4/code-13","url":"https://github.com/MindCode-4/code-13/tree/main/WinoGrande"},{"title":"MindSpore-scientific/code-5","url":"https://github.com/MindSpore-scientific/code-5/tree/main/WinoGrande"},{"title":"MindSpore-scientific/code-14","url":"https://github.com/MindSpore-scientific/code-14/tree/main/WinoGrande"},{"title":"MindSpore-scientific-2/code-3","url":"https://github.com/MindSpore-scientific-2/code-3/tree/main/WinoGrande"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52402,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"FLAN 137B (zero-shot)","metrics":{"Accuracy":"80.8"},"paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","paper_date":"2021-09-03","code_links":[{"title":"hiyouga/llama-efficient-tuning","url":"https://github.com/hiyouga/llama-efficient-tuning"},{"title":"bigcode-project/starcoder","url":"https://github.com/bigcode-project/starcoder"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"ukplab/arxiv2025-inherent-limits-plms","url":"https://github.com/ukplab/arxiv2025-inherent-limits-plms"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"MS-P3/code6","url":"https://github.com/MS-P3/code6/tree/main/finetune"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52403,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"GPT-3 175B (few-shot)","metrics":{"Accuracy":"80.1"},"paper_url":"https://arxiv.org/abs/2005.14165v4","paper_title":"Language Models are Few-Shot Learners","paper_date":"2020-05-28","code_links":[{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"karpathy/llm.c","url":"https://github.com/karpathy/llm.c"},{"title":"openai/gpt-3","url":"https://github.com/openai/gpt-3"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/gpt-3"},{"title":"EleutherAI/lm_evaluation_harness","url":"https://github.com/EleutherAI/lm_evaluation_harness"},{"title":"EleutherAI/lm-evaluation-harness","url":"https://github.com/EleutherAI/lm-evaluation-harness"},{"title":"EleutherAI/gpt-neo","url":"https://github.com/EleutherAI/gpt-neo"},{"title":"karpathy/build-nanogpt","url":"https://github.com/karpathy/build-nanogpt"},{"title":"ncoop57/gpt-code-clippy","url":"https://github.com/ncoop57/gpt-code-clippy"},{"title":"codedotal/gpt-code-clippy","url":"https://github.com/codedotal/gpt-code-clippy"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"shreyashankar/gpt3-sandbox","url":"https://github.com/shreyashankar/gpt3-sandbox"},{"title":"bigscience-workshop/Megatron-DeepSpeed","url":"https://github.com/bigscience-workshop/Megatron-DeepSpeed"},{"title":"NVIDIA/NeMo-Curator","url":"https://github.com/NVIDIA/NeMo-Curator"},{"title":"RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox"},{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"allenai/macaw","url":"https://github.com/allenai/macaw"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"tonyzhaozh/few-shot-learning","url":"https://github.com/tonyzhaozh/few-shot-learning"},{"title":"haiyang-w/git","url":"https://github.com/haiyang-w/git"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/gpt"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"ethanjperez/true_few_shot","url":"https://github.com/ethanjperez/true_few_shot"},{"title":"ai21labs/lm-evaluation","url":"https://github.com/ai21labs/lm-evaluation"},{"title":"lambert-x/prolab","url":"https://github.com/lambert-x/prolab"},{"title":"asahi417/relbert","url":"https://github.com/asahi417/relbert"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"milmor/GPT","url":"https://github.com/milmor/GPT"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"abhaskumarsinha/MinimalGPT","url":"https://github.com/abhaskumarsinha/MinimalGPT"},{"title":"turkunlp/megatron-deepspeed","url":"https://github.com/turkunlp/megatron-deepspeed"},{"title":"contextlab/abstract2paper","url":"https://github.com/contextlab/abstract2paper"},{"title":"kyegomez/GPT3","url":"https://github.com/kyegomez/GPT3"},{"title":"Samyu0304/thought-propagation","url":"https://github.com/Samyu0304/thought-propagation"},{"title":"smarton-empower/smarton-ai","url":"https://github.com/smarton-empower/smarton-ai"},{"title":"smile-data/smile","url":"https://github.com/smile-data/smile"},{"title":"postech-ami/smile-dataset","url":"https://github.com/postech-ami/smile-dataset"},{"title":"opengptx/lm-evaluation-harness","url":"https://github.com/opengptx/lm-evaluation-harness"},{"title":"gmum/dl-mo-2021","url":"https://github.com/gmum/dl-mo-2021"},{"title":"fywalter/label-bias","url":"https://github.com/fywalter/label-bias"},{"title":"nlx-group/overlapy","url":"https://github.com/nlx-group/overlapy"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"insait-institute/lm-evaluation-harness-bg","url":"https://github.com/insait-institute/lm-evaluation-harness-bg"},{"title":"x-lance/neusym-rag","url":"https://github.com/x-lance/neusym-rag"},{"title":"crazydigger/Callibration-of-GPT","url":"https://github.com/crazydigger/Callibration-of-GPT"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"vilm-ai/viet-llm-eval","url":"https://github.com/vilm-ai/viet-llm-eval"},{"title":"roberttwomey/machine-imagination-workshop","url":"https://github.com/roberttwomey/machine-imagination-workshop"},{"title":"VachanVY/gpt.jax","url":"https://github.com/VachanVY/gpt.jax"},{"title":"neuralmagic/lm-evaluation-harness","url":"https://github.com/neuralmagic/lm-evaluation-harness"},{"title":"scrayish/ML_NLP","url":"https://github.com/scrayish/ML_NLP"},{"title":"sambanova/lm-evaluation-harness","url":"https://github.com/sambanova/lm-evaluation-harness"},{"title":"roberttwomey/machine-imagination-isea","url":"https://github.com/roberttwomey/machine-imagination-isea"},{"title":"ltruncel/Microsoft_Azure_50daysofudacity","url":"https://github.com/ltruncel/Microsoft_Azure_50daysofudacity"},{"title":"ramanakshay/nanogpt","url":"https://github.com/ramanakshay/nanogpt"},{"title":"juletx/lm-evaluation-harness","url":"https://github.com/juletx/lm-evaluation-harness"},{"title":"national-center-for-ai-saudi-arabia/lm-evaluation-harness","url":"https://github.com/national-center-for-ai-saudi-arabia/lm-evaluation-harness"},{"title":"hilberthit/gpt-3","url":"https://github.com/hilberthit/gpt-3"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"EightRice/atn_GPT-3","url":"https://github.com/EightRice/atn_GPT-3"},{"title":"Mind23-2/MindCode-138","url":"https://github.com/Mind23-2/MindCode-138"},{"title":"mbzuai-paris/lm-evaluation-harness-atlas-chat","url":"https://github.com/mbzuai-paris/lm-evaluation-harness-atlas-chat"},{"title":"Sypherd/lm-evaluation-harness","url":"https://github.com/Sypherd/lm-evaluation-harness"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"},{"title":"zphang/lm_evaluation_harness","url":"https://github.com/zphang/lm_evaluation_harness"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52404,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"RoBERTa-large + G-DAug-Inf","metrics":{"Accuracy":"80"},"paper_url":"https://arxiv.org/abs/2004.11546v3","paper_title":"Generative Data Augmentation for Commonsense Reasoning","paper_date":"2020-04-24","code_links":[{"title":"yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning","url":"https://github.com/yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52405,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"UL2 20B (0-shot)","metrics":{"Accuracy":"79.9"},"paper_url":"https://arxiv.org/abs/2205.05131v3","paper_title":"UL2: Unifying Language Learning Paradigms","paper_date":"2022-05-10","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research"},{"title":"opennlg/openba-v2","url":"https://github.com/opennlg/openba-v2"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52406,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"ALBERT-xxlarge 235M","metrics":{"Accuracy":"78.8"},"paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","paper_date":"2021-04-16","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52407,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Neo-6B (QA + WS)","metrics":{"Accuracy":"77.9"},"paper_url":"https://arxiv.org/abs/2210.02441v3","paper_title":"Ask Me Anything: A simple strategy for prompting language models","paper_date":"2022-10-05","code_links":[{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"simran-arora/privacy_fm","url":"https://github.com/simran-arora/privacy_fm"},{"title":"simran-arora/focus","url":"https://github.com/simran-arora/focus"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52408,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"HNN","metrics":{"Accuracy":"75.1"},"paper_url":"https://arxiv.org/abs/1907.11983v1","paper_title":"A Hybrid Neural Network Model for Commonsense Reasoning","paper_date":"2019-07-27","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\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52409,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Neo-6B (QA)","metrics":{"Accuracy":"74.7"},"paper_url":"https://arxiv.org/abs/2210.02441v3","paper_title":"Ask Me Anything: A simple strategy for prompting language models","paper_date":"2022-10-05","code_links":[{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"simran-arora/privacy_fm","url":"https://github.com/simran-arora/privacy_fm"},{"title":"simran-arora/focus","url":"https://github.com/simran-arora/focus"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52410,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"RoBERTa-large 354M","metrics":{"Accuracy":"73.9"},"paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","paper_date":"2021-04-16","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52411,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"GPT-2-XL 1.5B","metrics":{"Accuracy":"73.3"},"paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","paper_date":"2023-04-27","code_links":[{"title":"mbzuai-nlp/lamini-lm","url":"https://github.com/mbzuai-nlp/lamini-lm"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52412,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"BERTwiki 340M (fine-tuned on WSCR)","metrics":{"Accuracy":"72.5"},"paper_url":"https://arxiv.org/abs/1905.06290v2","paper_title":"A Surprisingly Robust Trick for Winograd Schema Challenge","paper_date":"2019-05-15","code_links":[{"title":"vid-koci/bert-commonsense","url":"https://github.com/vid-koci/bert-commonsense"},{"title":"TangJiaLong/Knowledge-Projection-for-ERE","url":"https://github.com/TangJiaLong/Knowledge-Projection-for-ERE"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52413,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"BERT-SocialIQA 340M","metrics":{"Accuracy":"72.5"},"paper_url":"https://arxiv.org/abs/1904.09728v3","paper_title":"SocialIQA: Commonsense Reasoning about Social Interactions","paper_date":"2019-04-22","code_links":[{"title":"clear-nus/llm-human-model","url":"https://github.com/clear-nus/llm-human-model"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52414,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"BERT-large 340M (fine-tuned on WSCR)","metrics":{"Accuracy":"71.4"},"paper_url":"https://arxiv.org/abs/1905.06290v2","paper_title":"A Surprisingly Robust Trick for Winograd Schema Challenge","paper_date":"2019-05-15","code_links":[{"title":"vid-koci/bert-commonsense","url":"https://github.com/vid-koci/bert-commonsense"},{"title":"TangJiaLong/Knowledge-Projection-for-ERE","url":"https://github.com/TangJiaLong/Knowledge-Projection-for-ERE"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52415,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"GPT-2-XL 1.5B","metrics":{"Accuracy":"70.7"},"paper_url":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","paper_title":"Language Models are Unsupervised Multitask Learners","paper_date":"2019-02-14","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"openai/gpt-2","url":"https://github.com/openai/gpt-2"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/gpt"},{"title":"minimaxir/gpt-2-simple","url":"https://github.com/minimaxir/gpt-2-simple"},{"title":"imcaspar/gpt2-ml","url":"https://github.com/imcaspar/gpt2-ml"},{"title":"huggingface/swift-coreml-transformers","url":"https://github.com/huggingface/swift-coreml-transformers"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/blob/master/research/nlp/gpt2"},{"title":"jankrepl/mildlyoverfitted","url":"https://github.com/jankrepl/mildlyoverfitted"},{"title":"affjljoo3581/GPT2","url":"https://github.com/affjljoo3581/GPT2"},{"title":"akanyaani/gpt-2-tensorflow2.0","url":"https://github.com/akanyaani/gpt-2-tensorflow2.0"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms"},{"title":"milmor/GPT","url":"https://github.com/milmor/GPT"},{"title":"abhaskumarsinha/MinimalGPT","url":"https://github.com/abhaskumarsinha/MinimalGPT"},{"title":"aananda-giri/gpt2-nepali","url":"https://github.com/aananda-giri/gpt2-nepali"},{"title":"akanyaani/minGPTF","url":"https://github.com/akanyaani/minGPTF"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"VachanVY/gpt.jax","url":"https://github.com/VachanVY/gpt.jax"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/gpt2"},{"title":"ramanakshay/nanogpt","url":"https://github.com/ramanakshay/nanogpt"},{"title":"2023-MindSpore-1/ms-code-154","url":"https://github.com/2023-MindSpore-1/ms-code-154"},{"title":"varun-suresh/experiments-with-gpt2","url":"https://github.com/varun-suresh/experiments-with-gpt2"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52416,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"BERTwiki 340M (fine-tuned on half of WSCR)","metrics":{"Accuracy":"70.3"},"paper_url":"https://arxiv.org/abs/1905.06290v2","paper_title":"A Surprisingly Robust Trick for Winograd Schema Challenge","paper_date":"2019-05-15","code_links":[{"title":"vid-koci/bert-commonsense","url":"https://github.com/vid-koci/bert-commonsense"},{"title":"TangJiaLong/Knowledge-Projection-for-ERE","url":"https://github.com/TangJiaLong/Knowledge-Projection-for-ERE"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52417,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"LaMini-GPT 1.5B","metrics":{"Accuracy":"69.6"},"paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","paper_date":"2023-04-27","code_links":[{"title":"mbzuai-nlp/lamini-lm","url":"https://github.com/mbzuai-nlp/lamini-lm"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52418,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"GPT-2 Medium 774M (partial scoring)","metrics":{"Accuracy":"69.2"},"paper_url":"https://arxiv.org/abs/1811.01778v2","paper_title":"How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG","paper_date":"2018-11-05","code_links":[{"title":"ptrichel/How-Reasonable-are-Common-Sense-Reasoning-Tasks","url":"https://github.com/ptrichel/How-Reasonable-are-Common-Sense-Reasoning-Tasks"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52419,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"N-Grammer 343M","metrics":{"Accuracy":"68.3"},"paper_url":"https://arxiv.org/abs/2207.06366v1","paper_title":"N-Grammer: Augmenting Transformers with latent n-grams","paper_date":"2022-07-13","code_links":[{"title":"tensorflow/lingvo","url":"https://github.com/tensorflow/lingvo"},{"title":"yiyixuxu/n-grammer-flax","url":"https://github.com/yiyixuxu/n-grammer-flax"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52420,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"AlexaTM 20B","metrics":{"Accuracy":"68.3"},"paper_url":"https://arxiv.org/abs/2208.01448v2","paper_title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","paper_date":"2022-08-02","code_links":[{"title":"amazon-science/alexa-teacher-models","url":"https://github.com/amazon-science/alexa-teacher-models"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52421,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"BERT-large 340M","metrics":{"Accuracy":"67"},"paper_url":"https://arxiv.org/abs/1904.09728v3","paper_title":"SocialIQA: Commonsense Reasoning about Social Interactions","paper_date":"2019-04-22","code_links":[{"title":"clear-nus/llm-human-model","url":"https://github.com/clear-nus/llm-human-model"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52422,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"T5-Large 738M","metrics":{"Accuracy":"66.7"},"paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","paper_date":"2023-04-27","code_links":[{"title":"mbzuai-nlp/lamini-lm","url":"https://github.com/mbzuai-nlp/lamini-lm"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52423,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"T0-3B (CoT fine-tuned)","metrics":{"Accuracy":"66"},"paper_url":"https://arxiv.org/abs/2305.14045v2","paper_title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","paper_date":"2023-05-23","code_links":[{"title":"kaistai/cot-collection","url":"https://github.com/kaistai/cot-collection"},{"title":"kaist-lklab/cot-collection","url":"https://github.com/kaist-lklab/cot-collection"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52424,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"KiC-770M","metrics":{"Accuracy":"65.40"},"paper_url":"https://arxiv.org/abs/2210.16433v3","paper_title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","paper_date":"2022-10-28","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52425,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"GPT-2 Medium 774M (full scoring)","metrics":{"Accuracy":"64.5"},"paper_url":"https://arxiv.org/abs/1811.01778v2","paper_title":"How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG","paper_date":"2018-11-05","code_links":[{"title":"ptrichel/How-Reasonable-are-Common-Sense-Reasoning-Tasks","url":"https://github.com/ptrichel/How-Reasonable-are-Common-Sense-Reasoning-Tasks"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52426,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"LaMini-F-T5 783M","metrics":{"Accuracy":"64.1"},"paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","paper_date":"2023-04-27","code_links":[{"title":"mbzuai-nlp/lamini-lm","url":"https://github.com/mbzuai-nlp/lamini-lm"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52427,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Ensemble of 14 LMs","metrics":{"Accuracy":"63.7"},"paper_url":"https://arxiv.org/abs/1806.02847v2","paper_title":"A Simple Method for Commonsense Reasoning","paper_date":"2018-06-07","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/lm_commonsense"},{"title":"gabimelo/portuguese_wsc","url":"https://github.com/gabimelo/portuguese_wsc"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52428,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"H3 125M (3-shot, rank classification)","metrics":{"Accuracy":"63.5"},"paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","paper_date":"2022-12-28","code_links":[{"title":"hazyresearch/safari","url":"https://github.com/hazyresearch/safari"},{"title":"hazyresearch/h3","url":"https://github.com/hazyresearch/h3"},{"title":"lindermanlab/S5","url":"https://github.com/lindermanlab/S5"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52429,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"DSSM","metrics":{"Accuracy":"63.0"},"paper_url":"http://arxiv.org/abs/1904.01938v1","paper_title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","paper_date":"2019-04-03","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52430,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"RoBERTa-base 125M","metrics":{"Accuracy":"63"},"paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","paper_date":"2021-04-16","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52431,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Word-level CNN+LSTM (partial scoring)","metrics":{"Accuracy":"62.6"},"paper_url":"https://arxiv.org/abs/1806.02847v2","paper_title":"A Simple Method for Commonsense Reasoning","paper_date":"2018-06-07","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/lm_commonsense"},{"title":"gabimelo/portuguese_wsc","url":"https://github.com/gabimelo/portuguese_wsc"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52432,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"UDSSM-II (ensemble)","metrics":{"Accuracy":"62.4"},"paper_url":"http://arxiv.org/abs/1904.01938v1","paper_title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","paper_date":"2019-04-03","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52433,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"BERT-base 110M (fine-tuned on WSCR)","metrics":{"Accuracy":"62.3"},"paper_url":"https://arxiv.org/abs/1905.06290v2","paper_title":"A Surprisingly Robust Trick for Winograd Schema Challenge","paper_date":"2019-05-15","code_links":[{"title":"vid-koci/bert-commonsense","url":"https://github.com/vid-koci/bert-commonsense"},{"title":"TangJiaLong/Knowledge-Projection-for-ERE","url":"https://github.com/TangJiaLong/Knowledge-Projection-for-ERE"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52434,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"RoE-3B","metrics":{"Accuracy":"62.21"},"paper_url":"https://arxiv.org/abs/2302.03202v2","paper_title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","paper_date":"2023-02-07","code_links":[{"title":"joeljang/rlphf","url":"https://github.com/joeljang/rlphf"},{"title":"joeljang/elm","url":"https://github.com/joeljang/elm"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52435,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"BERT-large 340M","metrics":{"Accuracy":"62.0"},"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\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52436,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"GPT-2 Small 117M (partial scoring)","metrics":{"Accuracy":"61.5"},"paper_url":"https://arxiv.org/abs/1811.01778v2","paper_title":"How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG","paper_date":"2018-11-05","code_links":[{"title":"ptrichel/How-Reasonable-are-Common-Sense-Reasoning-Tasks","url":"https://github.com/ptrichel/How-Reasonable-are-Common-Sense-Reasoning-Tasks"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52437,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"H3 125M (0-shot, rank classification)","metrics":{"Accuracy":"61.5"},"paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","paper_date":"2022-12-28","code_links":[{"title":"hazyresearch/safari","url":"https://github.com/hazyresearch/safari"},{"title":"hazyresearch/h3","url":"https://github.com/hazyresearch/h3"},{"title":"lindermanlab/S5","url":"https://github.com/lindermanlab/S5"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52438,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"BERT-large 340M","metrics":{"Accuracy":"61.4"},"paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","paper_date":"2021-04-16","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52439,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"BERT-base 110M + MAS","metrics":{"Accuracy":"60.3"},"paper_url":"https://arxiv.org/abs/1905.13497v1","paper_title":"Attention Is (not) All You Need for Commonsense Reasoning","paper_date":"2019-05-31","code_links":[{"title":"SAP-samples/acl2020-commonsense","url":"https://github.com/SAP-samples/acl2020-commonsense"},{"title":"SAP-samples/acl2019-commonsense-reasoning","url":"https://github.com/SAP-samples/acl2019-commonsense-reasoning"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52440,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"longdoc S (OntoNotes + PreCo + LitBank)","metrics":{"Accuracy":"60.1"},"paper_url":"https://arxiv.org/abs/2109.09667v1","paper_title":"On Generalization in Coreference Resolution","paper_date":"2021-09-20","code_links":[{"title":"shtoshni/fast-coref","url":"https://github.com/shtoshni/fast-coref"},{"title":"shtoshni92/fast-coref","url":"https://github.com/shtoshni92/fast-coref"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52441,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"longdoc S (ON + PreCo + LitBank + 30k pseudo-singletons)","metrics":{"Accuracy":"59.4"},"paper_url":"https://arxiv.org/abs/2109.09667v1","paper_title":"On Generalization in Coreference Resolution","paper_date":"2021-09-20","code_links":[{"title":"shtoshni/fast-coref","url":"https://github.com/shtoshni/fast-coref"},{"title":"shtoshni92/fast-coref","url":"https://github.com/shtoshni92/fast-coref"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52442,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"UDSSM-II","metrics":{"Accuracy":"59.2"},"paper_url":"http://arxiv.org/abs/1904.01938v1","paper_title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","paper_date":"2019-04-03","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52443,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"LaMini-T5 738M","metrics":{"Accuracy":"59"},"paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","paper_date":"2023-04-27","code_links":[{"title":"mbzuai-nlp/lamini-lm","url":"https://github.com/mbzuai-nlp/lamini-lm"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52444,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Flipped-3B","metrics":{"Accuracy":"58.37"},"paper_url":"https://arxiv.org/abs/2210.02969v4","paper_title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","paper_date":"2022-10-06","code_links":[{"title":"seonghyeonye/flipped-learning","url":"https://github.com/seonghyeonye/flipped-learning"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52445,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"KEE+NKAM winner of the WSC2016","metrics":{"Accuracy":"58.3"},"paper_url":"http://arxiv.org/abs/1611.04146v2","paper_title":"Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge","paper_date":"2016-11-13","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52446,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Char-level CNN+LSTM (partial scoring)","metrics":{"Accuracy":"57.9"},"paper_url":"https://arxiv.org/abs/1806.02847v2","paper_title":"A Simple Method for Commonsense Reasoning","paper_date":"2018-06-07","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/lm_commonsense"},{"title":"gabimelo/portuguese_wsc","url":"https://github.com/gabimelo/portuguese_wsc"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52447,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"UDSSM-I (ensemble)","metrics":{"Accuracy":"57.1"},"paper_url":"http://arxiv.org/abs/1904.01938v1","paper_title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","paper_date":"2019-04-03","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52448,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Knowledge Hunter","metrics":{"Accuracy":"57.1"},"paper_url":"http://arxiv.org/abs/1810.01375v1","paper_title":"A Knowledge Hunting Framework for Common Sense Reasoning","paper_date":"2018-10-02","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52449,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"WKH","metrics":{"Accuracy":"57.1"},"paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","paper_date":"2019-07-24","code_links":[{"title":"vered1986/self_talk","url":"https://github.com/vered1986/self_talk"},{"title":"mindspore-ai/contrib","url":"https://github.com/mindspore-ai/contrib/tree/master/application/WinoGrande"},{"title":"swarnahub/explanationhardness","url":"https://github.com/swarnahub/explanationhardness"},{"title":"crherlihy/clinical_nli_artifacts","url":"https://github.com/crherlihy/clinical_nli_artifacts"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/4/WinoGrande"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/3/WinoGrande"},{"title":"MindCode-4/code-13","url":"https://github.com/MindCode-4/code-13/tree/main/WinoGrande"},{"title":"MindSpore-scientific/code-5","url":"https://github.com/MindSpore-scientific/code-5/tree/main/WinoGrande"},{"title":"MindSpore-scientific/code-14","url":"https://github.com/MindSpore-scientific/code-14/tree/main/WinoGrande"},{"title":"MindSpore-scientific-2/code-3","url":"https://github.com/MindSpore-scientific-2/code-3/tree/main/WinoGrande"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52450,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"BERT-base 110M","metrics":{"Accuracy":"56.5"},"paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","paper_date":"2021-04-16","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52451,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"GPT-2 Small 117M (full scoring)","metrics":{"Accuracy":"55.7"},"paper_url":"https://arxiv.org/abs/1811.01778v2","paper_title":"How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG","paper_date":"2018-11-05","code_links":[{"title":"ptrichel/How-Reasonable-are-Common-Sense-Reasoning-Tasks","url":"https://github.com/ptrichel/How-Reasonable-are-Common-Sense-Reasoning-Tasks"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52452,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"ALBERT-base 11M","metrics":{"Accuracy":"55.4"},"paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","paper_date":"2021-04-16","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52453,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Pythia 12B (0-shot)","metrics":{"Accuracy":"54.8"},"paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","paper_date":"2023-04-03","code_links":[{"title":"Lightning-AI/lit-gpt","url":"https://github.com/Lightning-AI/lit-gpt"},{"title":"jzhang38/tinyllama","url":"https://github.com/jzhang38/tinyllama"},{"title":"eleutherai/gpt-neox","url":"https://github.com/eleutherai/gpt-neox"},{"title":"eleutherai/pythia","url":"https://github.com/eleutherai/pythia"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52454,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"UDSSM-I","metrics":{"Accuracy":"54.5"},"paper_url":"http://arxiv.org/abs/1904.01938v1","paper_title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","paper_date":"2019-04-03","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52455,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Subword-level Transformer LM","metrics":{"Accuracy":"54.1"},"paper_url":"https://arxiv.org/abs/1706.03762v7","paper_title":"Attention Is All You Need","paper_date":"2017-06-12","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"facebookresearch/fairseq","url":"https://github.com/facebookresearch/fairseq"},{"title":"karpathy/minGPT","url":"https://github.com/karpathy/minGPT"},{"title":"tensorflow/tensor2tensor","url":"https://github.com/tensorflow/tensor2tensor"},{"title":"graykode/nlp-tutorial","url":"https://github.com/graykode/nlp-tutorial"},{"title":"PaddlePaddle/PaddleSpeech","url":"https://github.com/PaddlePaddle/PaddleSpeech"},{"title":"xmu-xiaoma666/External-Attention-pytorch","url":"https://github.com/xmu-xiaoma666/External-Attention-pytorch"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/machine_translation/transformer"},{"title":"alibaba-damo-academy/FunASR","url":"https://github.com/alibaba-damo-academy/FunASR"},{"title":"facebookresearch/xformers","url":"https://github.com/facebookresearch/xformers"},{"title":"jadore801120/attention-is-all-you-need-pytorch","url":"https://github.com/jadore801120/attention-is-all-you-need-pytorch"},{"title":"google/flax","url":"https://github.com/google/flax/tree/master/examples/wmt"},{"title":"harvardnlp/annotated-transformer","url":"https://github.com/harvardnlp/annotated-transformer"},{"title":"Kyubyong/transformer","url":"https://github.com/Kyubyong/transformer"},{"title":"opennmt/ctranslate2","url":"https://github.com/opennmt/ctranslate2"},{"title":"hyunwoongko/transformer","url":"https://github.com/hyunwoongko/transformer"},{"title":"open-mmlab/mmclassification","url":"https://github.com/open-mmlab/mmclassification"},{"title":"karpathy/makemore","url":"https://github.com/karpathy/makemore"},{"title":"deepmind/haiku","url":"https://github.com/deepmind/haiku"},{"title":"going-doer/paper2code","url":"https://github.com/going-doer/paper2code"},{"title":"shreyashankar/gpt3-sandbox","url":"https://github.com/shreyashankar/gpt3-sandbox"},{"title":"dmlc/gluon-nlp","url":"https://github.com/dmlc/gluon-nlp"},{"title":"ming024/FastSpeech2","url":"https://github.com/ming024/FastSpeech2"},{"title":"exa-labs/exa-mcp-server","url":"https://github.com/exa-labs/exa-mcp-server"},{"title":"WenjieDu/PyPOTS","url":"https://github.com/WenjieDu/PyPOTS"},{"title":"davisking/dlib-models","url":"https://github.com/davisking/dlib-models"},{"title":"IBM/pytorch-seq2seq","url":"https://github.com/IBM/pytorch-seq2seq"},{"title":"glouppe/info8010-deep-learning","url":"https://github.com/glouppe/info8010-deep-learning"},{"title":"awslabs/sockeye","url":"https://github.com/awslabs/sockeye"},{"title":"The-AI-Summer/self_attention","url":"https://github.com/The-AI-Summer/self_attention"},{"title":"NVIDIA/sentiment-discovery","url":"https://github.com/NVIDIA/sentiment-discovery"},{"title":"gordicaleksa/pytorch-original-transformer","url":"https://github.com/gordicaleksa/pytorch-original-transformer"},{"title":"veekaybee/what_are_embeddings","url":"https://github.com/veekaybee/what_are_embeddings"},{"title":"graykode/gpt-2-Pytorch","url":"https://github.com/graykode/gpt-2-Pytorch"},{"title":"maxjcohen/transformer","url":"https://github.com/maxjcohen/transformer"},{"title":"xcmyz/FastSpeech","url":"https://github.com/xcmyz/FastSpeech"},{"title":"lukemelas/PyTorch-Pretrained-ViT","url":"https://github.com/lukemelas/PyTorch-Pretrained-ViT"},{"title":"kaituoxu/Speech-Transformer","url":"https://github.com/kaituoxu/Speech-Transformer"},{"title":"kaituoxu/SpeechTransformer","url":"https://github.com/kaituoxu/SpeechTransformer"},{"title":"vinairesearch/phogpt","url":"https://github.com/vinairesearch/phogpt"},{"title":"studio-ousia/luke","url":"https://github.com/studio-ousia/luke"},{"title":"Lsdefine/attention-is-all-you-need-keras","url":"https://github.com/Lsdefine/attention-is-all-you-need-keras"},{"title":"THUNLP-MT/THUMT","url":"https://github.com/THUNLP-MT/THUMT"},{"title":"thumt/THUMT","url":"https://github.com/thumt/THUMT"},{"title":"tatp22/multidim-positional-encoding","url":"https://github.com/tatp22/multidim-positional-encoding"},{"title":"HKUST-KnowComp/R-Net","url":"https://github.com/HKUST-KnowComp/R-Net"},{"title":"re-search/DocProduct","url":"https://github.com/re-search/DocProduct"},{"title":"chengchingwen/transformers.jl","url":"https://github.com/chengchingwen/transformers.jl"},{"title":"kpot/keras-transformer","url":"https://github.com/kpot/keras-transformer"},{"title":"sh951011/Attention-Implementation","url":"https://github.com/sh951011/Attention-Implementation"},{"title":"sooftware/attentions","url":"https://github.com/sooftware/attentions"},{"title":"sooftware/Attention-Implementation","url":"https://github.com/sooftware/Attention-Implementation"},{"title":"sooftware/nlp-attentions","url":"https://github.com/sooftware/nlp-attentions"},{"title":"conceptofmind/lamda-rlhf-pytorch","url":"https://github.com/conceptofmind/lamda-rlhf-pytorch"},{"title":"conceptofmind/LaMDA-pytorch","url":"https://github.com/conceptofmind/LaMDA-pytorch"},{"title":"tatp22/linformer-pytorch","url":"https://github.com/tatp22/linformer-pytorch"},{"title":"pengming617/bert_classification","url":"https://github.com/pengming617/bert_classification"},{"title":"microsoft/onnxruntime-training-examples","url":"https://github.com/microsoft/onnxruntime-training-examples"},{"title":"LiamMaclean216/Pytorch-Transfomer","url":"https://github.com/LiamMaclean216/Pytorch-Transfomer"},{"title":"cmsflash/efficient-attention","url":"https://github.com/cmsflash/efficient-attention"},{"title":"bytedance/neurst","url":"https://github.com/bytedance/neurst"},{"title":"CGCL-codes/naturalcc","url":"https://github.com/CGCL-codes/naturalcc"},{"title":"kolloldas/torchnlp","url":"https://github.com/kolloldas/torchnlp"},{"title":"wzlxjtu/PositionalEncoding2D","url":"https://github.com/wzlxjtu/PositionalEncoding2D"},{"title":"BrianPulfer/PapersReimplementations","url":"https://github.com/BrianPulfer/PapersReimplementations"},{"title":"bkoch4142/attention-is-all-you-need-paper","url":"https://github.com/bkoch4142/attention-is-all-you-need-paper"},{"title":"MarcBS/keras","url":"https://github.com/MarcBS/keras"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/transformer"},{"title":"dccuchile/CC6204","url":"https://github.com/dccuchile/CC6204"},{"title":"keonlee9420/Parallel-Tacotron2","url":"https://github.com/keonlee9420/Parallel-Tacotron2"},{"title":"hannibal046/nanorwkv","url":"https://github.com/hannibal046/nanorwkv"},{"title":"Glaceon31/Document-Transformer","url":"https://github.com/Glaceon31/Document-Transformer"},{"title":"chiayewken/bert-qa","url":"https://github.com/chiayewken/bert-qa"},{"title":"rojagtap/abstractive_summarizer","url":"https://github.com/rojagtap/abstractive_summarizer"},{"title":"cahya-wirawan/indonesian-language-models","url":"https://github.com/cahya-wirawan/indonesian-language-models"},{"title":"alibabasglab/frcrn","url":"https://github.com/alibabasglab/frcrn"},{"title":"bzhangGo/zero","url":"https://github.com/bzhangGo/zero"},{"title":"manideep2510/siamese-BERT-fake-news-detection-LIAR","url":"https://github.com/manideep2510/siamese-BERT-fake-news-detection-LIAR"},{"title":"guillaume-chevalier/Linear-Attention-Recurrent-Neural-Network","url":"https://github.com/guillaume-chevalier/Linear-Attention-Recurrent-Neural-Network"},{"title":"kh-kim/simple-nmt","url":"https://github.com/kh-kim/simple-nmt"},{"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":"lvyufeng/mindspore-nlp-tutorial","url":"https://github.com/lvyufeng/mindspore-nlp-tutorial"},{"title":"ArdalanM/nlp-benchmarks","url":"https://github.com/ArdalanM/nlp-benchmarks"},{"title":"KeithGalli/pycon2020","url":"https://github.com/KeithGalli/pycon2020"},{"title":"moein-shariatnia/Pix2Seq","url":"https://github.com/moein-shariatnia/Pix2Seq"},{"title":"asfathermou/human-computer-interaction","url":"https://github.com/asfathermou/human-computer-interaction"},{"title":"tshu-w/dbcopilot","url":"https://github.com/tshu-w/dbcopilot"},{"title":"joongbo/tta","url":"https://github.com/joongbo/tta"},{"title":"dreamgonfly/Transformer-pytorch","url":"https://github.com/dreamgonfly/Transformer-pytorch"},{"title":"redevaaa/Transformer-for-EEG","url":"https://github.com/redevaaa/Transformer-for-EEG"},{"title":"ankurbhatia24/MULTIMODAL-EMOTION-RECOGNITION","url":"https://github.com/ankurbhatia24/MULTIMODAL-EMOTION-RECOGNITION"},{"title":"ricsinaruto/dialog-eval","url":"https://github.com/ricsinaruto/dialog-eval"},{"title":"stevinc/Transformer_Timeseries","url":"https://github.com/stevinc/Transformer_Timeseries"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"whr94621/NJUNMT-pytorch","url":"https://github.com/whr94621/NJUNMT-pytorch"},{"title":"wxt1997/Transformer-Transducer","url":"https://github.com/wxt1997/Transformer-Transducer"},{"title":"okkteam/Transformer-Transducer","url":"https://github.com/okkteam/Transformer-Transducer"},{"title":"vinayprabhu/X-is-all-you-need","url":"https://github.com/vinayprabhu/X-is-all-you-need"},{"title":"reppy4620/Dialog","url":"https://github.com/reppy4620/Dialog"},{"title":"Skumarr53/Attention-is-All-you-Need-PyTorch","url":"https://github.com/Skumarr53/Attention-is-All-you-Need-PyTorch"},{"title":"bangoc123/transformer","url":"https://github.com/bangoc123/transformer"},{"title":"cpm0722/transformer_pytorch","url":"https://github.com/cpm0722/transformer_pytorch"},{"title":"radoslawkrolikowski/sentiment-analysis-pytorch","url":"https://github.com/radoslawkrolikowski/sentiment-analysis-pytorch"},{"title":"hubiodatalab/druggen","url":"https://github.com/hubiodatalab/druggen"},{"title":"UdbhavPrasad072300/Transformer-Implementation","url":"https://github.com/UdbhavPrasad072300/Transformer-Implementation"},{"title":"UdbhavPrasad072300/Transformer-Implementations","url":"https://github.com/UdbhavPrasad072300/Transformer-Implementations"},{"title":"UdbhavPrasad072300/Transformer-Implementation-and-Language-Translation","url":"https://github.com/UdbhavPrasad072300/Transformer-Implementation-and-Language-Translation"},{"title":"hfxunlp/transformer","url":"https://github.com/hfxunlp/transformer"},{"title":"CVxTz/music_genre_classification","url":"https://github.com/CVxTz/music_genre_classification"},{"title":"phohenecker/pytorch-transformer","url":"https://github.com/phohenecker/pytorch-transformer"},{"title":"cyberzhg/keras-pos-embd","url":"https://github.com/cyberzhg/keras-pos-embd"},{"title":"ericperfect/Bert_Position_BiLSTM_Attention_CRF_LSTMDecoder","url":"https://github.com/ericperfect/Bert_Position_BiLSTM_Attention_CRF_LSTMDecoder"},{"title":"dyq0811/EEG-Transformer-seq2seq","url":"https://github.com/dyq0811/EEG-Transformer-seq2seq"},{"title":"duyunshu/bert-sentiment-analysis","url":"https://github.com/duyunshu/bert-sentiment-analysis"},{"title":"hyunwookl/testam","url":"https://github.com/hyunwookl/testam"},{"title":"ShivamRajSharma/Transformer-Architectures-From-Scratch","url":"https://github.com/ShivamRajSharma/Transformer-Architectures-From-Scratch"},{"title":"knotgrass/attention","url":"https://github.com/knotgrass/attention/blob/main/attn/attention.py"},{"title":"tensorops/TransformerX","url":"https://github.com/tensorops/TransformerX"},{"title":"franknb/Self-attention-DCGAN","url":"https://github.com/franknb/Self-attention-DCGAN"},{"title":"DevSinghSachan/multilingual_nmt","url":"https://github.com/DevSinghSachan/multilingual_nmt"},{"title":"anton-bushuiev/ppiformer","url":"https://github.com/anton-bushuiev/ppiformer"},{"title":"vulus98/rethinking-attention","url":"https://github.com/vulus98/rethinking-attention"},{"title":"StillKeepTry/Transformer-PyTorch","url":"https://github.com/StillKeepTry/Transformer-PyTorch"},{"title":"Iwontbecreative/Abstractive-summarization-OpenNMT","url":"https://github.com/Iwontbecreative/Abstractive-summarization-OpenNMT"},{"title":"valentinmace/noisy-text","url":"https://github.com/valentinmace/noisy-text"},{"title":"pomonam/AttentionCluster","url":"https://github.com/pomonam/AttentionCluster"},{"title":"piquil/rydberggpt","url":"https://github.com/piquil/rydberggpt"},{"title":"HzcIrving/DeepLearning_PlayGround","url":"https://github.com/HzcIrving/DeepLearning_PlayGround"},{"title":"dqqcasia/st","url":"https://github.com/dqqcasia/st"},{"title":"ky1994/SpeechRecognition","url":"https://github.com/ky1994/SpeechRecognition"},{"title":"GlassyWing/transformer-keras","url":"https://github.com/GlassyWing/transformer-keras"},{"title":"pennylaneai/generative-quantum-states","url":"https://github.com/pennylaneai/generative-quantum-states"},{"title":"04RR/SOTA-Vision","url":"https://github.com/04RR/SOTA-Vision"},{"title":"ypeleg/MinimalIsAllYouNeed","url":"https://github.com/ypeleg/MinimalIsAllYouNeed"},{"title":"Belval/NRTR","url":"https://github.com/Belval/NRTR"},{"title":"JRC1995/Machine-Translation-Transformers","url":"https://github.com/JRC1995/Machine-Translation-Transformers"},{"title":"FlorianPfisterer/2D-LSTM-Seq2Seq","url":"https://github.com/FlorianPfisterer/2D-LSTM-Seq2Seq"},{"title":"WenYanger/General-Transformer-Pytorch","url":"https://github.com/WenYanger/General-Transformer-Pytorch"},{"title":"czero69/acomoeye-NN","url":"https://github.com/czero69/acomoeye-NN"},{"title":"brightmart/bert_customized","url":"https://github.com/brightmart/bert_customized"},{"title":"parcorelab/comscribe","url":"https://github.com/parcorelab/comscribe"},{"title":"agentdr1/la_mil","url":"https://github.com/agentdr1/la_mil"},{"title":"nameoverflow/neuro-cangjie","url":"https://github.com/nameoverflow/neuro-cangjie"},{"title":"af-ai-center/nerblackbox","url":"https://github.com/af-ai-center/nerblackbox"},{"title":"flxst/nerblackbox","url":"https://github.com/flxst/nerblackbox"},{"title":"zysite/post","url":"https://github.com/zysite/post"},{"title":"abhaskumarsinha/MinimalGPT","url":"https://github.com/abhaskumarsinha/MinimalGPT"},{"title":"vpj/jax_transformer","url":"https://github.com/vpj/jax_transformer"},{"title":"Chang-Chia-Chi/SaintPlus-Knowledge-Tracing-Pytorch","url":"https://github.com/Chang-Chia-Chi/SaintPlus-Knowledge-Tracing-Pytorch"},{"title":"u7javed/Transformer-Multi-Language-Translator","url":"https://github.com/u7javed/Transformer-Multi-Language-Translator"},{"title":"gooppe/transformer-summarization","url":"https://github.com/gooppe/transformer-summarization"},{"title":"xingjian-zhang/massw","url":"https://github.com/xingjian-zhang/massw"},{"title":"ictnlp/TLAT-NMT","url":"https://github.com/ictnlp/TLAT-NMT"},{"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":"fjiangai/mmapis","url":"https://github.com/fjiangai/mmapis"},{"title":"ictnlp/DiverseNMT","url":"https://github.com/ictnlp/DiverseNMT"},{"title":"baotramduong/Sentiment-Analysis-with-Deep-Learning-using-BERT","url":"https://github.com/baotramduong/Sentiment-Analysis-with-Deep-Learning-using-BERT"},{"title":"LiamMaclean216/Pytorch-Chatbot","url":"https://github.com/LiamMaclean216/Pytorch-Chatbot"},{"title":"uzi0espil/research-papers-implementation","url":"https://github.com/uzi0espil/research-papers-implementation/tree/master/Attention%20Is%20All%20You%20Need"},{"title":"baotramduong/Twitter-Sentiment-Analysis-with-Deep-Learning-using-BERT","url":"https://github.com/baotramduong/Twitter-Sentiment-Analysis-with-Deep-Learning-using-BERT"},{"title":"richard-peng-xia/Chinese-Noisy-Text","url":"https://github.com/richard-peng-xia/Chinese-Noisy-Text"},{"title":"PrideLee/sentiment-analysis","url":"https://github.com/PrideLee/sentiment-analysis"},{"title":"richard88888/chinese-noisy-text","url":"https://github.com/richard88888/chinese-noisy-text"},{"title":"bdusell/stack-attention","url":"https://github.com/bdusell/stack-attention"},{"title":"mindspore-courses/External-Attention-MindSpore","url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/SelfAttention.py"},{"title":"tanjeffreyz/attention-is-all-you-need","url":"https://github.com/tanjeffreyz/attention-is-all-you-need"},{"title":"MirunaPislar/multi-head-attention-labeller","url":"https://github.com/MirunaPislar/multi-head-attention-labeller"},{"title":"Bhavnicksm/vanilla-transformer-jax","url":"https://github.com/Bhavnicksm/vanilla-transformer-jax"},{"title":"simonjisu/annotated-transformer-kr","url":"https://github.com/simonjisu/annotated-transformer-kr"},{"title":"swimmingCreative/DeepSpeechRecognition-master","url":"https://github.com/swimmingCreative/DeepSpeechRecognition-master"},{"title":"seominseok0429/inception-I3D-NON-LOCAL","url":"https://github.com/seominseok0429/inception-I3D-NON-LOCAL"},{"title":"ictnlp/PTE-NMT","url":"https://github.com/ictnlp/PTE-NMT"},{"title":"ricsinaruto/NeuralChatbots-DataFiltering","url":"https://github.com/ricsinaruto/NeuralChatbots-DataFiltering"},{"title":"IOB-Muenster/TEclass2","url":"https://github.com/IOB-Muenster/TEclass2"},{"title":"han-shi/SparseBERT","url":"https://github.com/han-shi/SparseBERT"},{"title":"felixSchober/ABSA-Transformer","url":"https://github.com/felixSchober/ABSA-Transformer"},{"title":"reactive-systems/ml2","url":"https://github.com/reactive-systems/ml2"},{"title":"Remiphilius/PoemesProfonds","url":"https://github.com/Remiphilius/PoemesProfonds"},{"title":"ictnlp/NA-MNMT","url":"https://github.com/ictnlp/NA-MNMT"},{"title":"af-ai-center/bert","url":"https://github.com/af-ai-center/bert"},{"title":"fancyerii/bert","url":"https://github.com/fancyerii/bert"},{"title":"ahmetumutdurmus/awd-lstm","url":"https://github.com/ahmetumutdurmus/awd-lstm"},{"title":"nsfzyzz/generalization_metrics_for_nlp","url":"https://github.com/nsfzyzz/generalization_metrics_for_nlp"},{"title":"sjyttkl/Transformer_learning","url":"https://github.com/sjyttkl/Transformer_learning"},{"title":"gooofy/zbrain","url":"https://github.com/gooofy/zbrain"},{"title":"sajadalipour7/persian-grapheme-to-phoneme-with-transformer","url":"https://github.com/sajadalipour7/persian-grapheme-to-phoneme-with-transformer"},{"title":"tshu-w/llm4em","url":"https://github.com/tshu-w/llm4em"},{"title":"dreamnotover/english_chinese_machine_translation_baseline","url":"https://github.com/dreamnotover/english_chinese_machine_translation_baseline"},{"title":"brainsqueeze/text2vec","url":"https://github.com/brainsqueeze/text2vec"},{"title":"xiaopingzhong/bert-finetune-for-classfier","url":"https://github.com/xiaopingzhong/bert-finetune-for-classfier"},{"title":"maroxtn/tun-sentiment","url":"https://github.com/maroxtn/tun-sentiment"},{"title":"xydaytoy/BMI-NMT","url":"https://github.com/xydaytoy/BMI-NMT"},{"title":"SYangDong/bert-with-frozen-code","url":"https://github.com/SYangDong/bert-with-frozen-code"},{"title":"abhilashreddys/Fake-News-Article","url":"https://github.com/abhilashreddys/Fake-News-Article"},{"title":"bcmi220/esc4nmt","url":"https://github.com/bcmi220/esc4nmt"},{"title":"gmum/dl-mo-2021","url":"https://github.com/gmum/dl-mo-2021"},{"title":"TheTensorDude/transformer-tf","url":"https://github.com/TheTensorDude/transformer-tf"},{"title":"autobotasia/vibert","url":"https://github.com/autobotasia/vibert"},{"title":"dhiraa/tener","url":"https://github.com/dhiraa/tener"},{"title":"ethancaballero/neural-engineers-first-attempt","url":"https://github.com/ethancaballero/neural-engineers-first-attempt"},{"title":"kelly2016/multi-label-bert","url":"https://github.com/kelly2016/multi-label-bert"},{"title":"baosongyang/WRD","url":"https://github.com/baosongyang/WRD"},{"title":"lehoanganh298/BERT-Question-Answering","url":"https://github.com/lehoanganh298/BERT-Question-Answering"},{"title":"TieDanCuihua/transformer-Attention-is-All-You-Need","url":"https://github.com/TieDanCuihua/transformer-Attention-is-All-You-Need"},{"title":"mindspore-courses/Deep-Tutorials-for-MindSpore","url":"https://github.com/mindspore-courses/Deep-Tutorials-for-MindSpore"},{"title":"zer0sh0t/artificial_intelligence","url":"https://github.com/zer0sh0t/artificial_intelligence/tree/master/transformer"},{"title":"karta282950/bert-multiclass","url":"https://github.com/karta282950/bert-multiclass"},{"title":"umeiko/mindspore-seq2seq","url":"https://github.com/umeiko/mindspore-seq2seq"},{"title":"akanyaani/minGPTF","url":"https://github.com/akanyaani/minGPTF"},{"title":"jiahuei/Self-Critical-SCST-TensorFlow","url":"https://github.com/jiahuei/Self-Critical-SCST-TensorFlow"},{"title":"truclycs/ocr_seq2seq","url":"https://github.com/truclycs/ocr_seq2seq"},{"title":"arkel23/PyTorch-Pretrained-ViT","url":"https://github.com/arkel23/PyTorch-Pretrained-ViT"},{"title":"deepmipt/bert","url":"https://github.com/deepmipt/bert/tree/feat/multi_gpu"},{"title":"reactive-systems/circuit-repair","url":"https://github.com/reactive-systems/circuit-repair"},{"title":"fanchenyou/transformer-study","url":"https://github.com/fanchenyou/transformer-study"},{"title":"Izecson/saml-nmt","url":"https://github.com/Izecson/saml-nmt"},{"title":"ArvidWartenberg/retrosynthesis","url":"https://github.com/ArvidWartenberg/retrosynthesis"},{"title":"brandontrabucco/scaled_dot_product_attention","url":"https://github.com/brandontrabucco/scaled_dot_product_attention"},{"title":"harenlin/IMDB-Sentiment-Analysis-Using-BERT-Fine-Tuning","url":"https://github.com/harenlin/IMDB-Sentiment-Analysis-Using-BERT-Fine-Tuning"},{"title":"neqkir/attention-mechanism","url":"https://github.com/neqkir/attention-mechanism"},{"title":"2miatran/Natural-Language-Processing","url":"https://github.com/2miatran/Natural-Language-Processing"},{"title":"MCLYang/RhythmGAN_pytorch","url":"https://github.com/MCLYang/RhythmGAN_pytorch"},{"title":"rajlm10/Chandler","url":"https://github.com/rajlm10/Chandler"},{"title":"patrickhart/jaxdl","url":"https://github.com/patrickhart/jaxdl"},{"title":"ShuvenduBikash/transformer_spelling_corrector","url":"https://github.com/ShuvenduBikash/transformer_spelling_corrector"},{"title":"jbdel/OMG_UMONS_submission","url":"https://github.com/jbdel/OMG_UMONS_submission"},{"title":"lucylow/En_francais_si_vous_plait-","url":"https://github.com/lucylow/En_francais_si_vous_plait-"},{"title":"abhaskumarsinha/Keras-implementation-of-Transformer-Architecture","url":"https://github.com/abhaskumarsinha/Keras-implementation-of-Transformer-Architecture/blob/main/Transformer.py"},{"title":"abhaskumarsinha/Keras-implementation-of-Transformer-Architecture","url":"https://github.com/abhaskumarsinha/Keras-implementation-of-Transformer-Architecture"},{"title":"ays-dev/keras-transformer","url":"https://github.com/ays-dev/keras-transformer"},{"title":"ewdowiak/Sicilian_Translator","url":"https://github.com/ewdowiak/Sicilian_Translator"},{"title":"krocki/np-transformer","url":"https://github.com/krocki/np-transformer"},{"title":"XapaJIaMnu/transformative","url":"https://github.com/XapaJIaMnu/transformative"},{"title":"LeoWood/bert-horovod","url":"https://github.com/LeoWood/bert-horovod"},{"title":"augustgw/early-exit-transformer","url":"https://github.com/augustgw/early-exit-transformer"},{"title":"Enigmatisms/Set-Transformer","url":"https://github.com/Enigmatisms/Set-Transformer"},{"title":"jelifysh/Transformers","url":"https://github.com/jelifysh/Transformers"},{"title":"Doffery/BERT-Sentiment-Analysis-Amazon-Review","url":"https://github.com/Doffery/BERT-Sentiment-Analysis-Amazon-Review"},{"title":"prabhupad26/100daysofML","url":"https://github.com/prabhupad26/100daysofML"},{"title":"Dave870907/Transformer","url":"https://github.com/Dave870907/Transformer"},{"title":"ikergarcia1996/Simultaneous-Machine-Translation","url":"https://github.com/ikergarcia1996/Simultaneous-Machine-Translation"},{"title":"MaZhiyuanBUAA/bert-tf1.4.0","url":"https://github.com/MaZhiyuanBUAA/bert-tf1.4.0"},{"title":"MichaelZhouwang/LMlexsub","url":"https://github.com/MichaelZhouwang/LMlexsub"},{"title":"jean-kunz/ml_research_papers","url":"https://github.com/jean-kunz/ml_research_papers"},{"title":"theQuert/inlpfun","url":"https://github.com/theQuert/inlpfun"},{"title":"colorfulscoop/tfdlg","url":"https://github.com/colorfulscoop/tfdlg"},{"title":"hiun/learning-transformers","url":"https://github.com/hiun/learning-transformers"},{"title":"the-Quert/iNLPfun","url":"https://github.com/the-Quert/iNLPfun"},{"title":"vvvm23/TchAIkovsky-Legacy","url":"https://github.com/vvvm23/TchAIkovsky-Legacy"},{"title":"akashe/Python-Code-Generation","url":"https://github.com/akashe/Python-Code-Generation"},{"title":"rupakdas18/SemEval-2017-Task-4-A-B-C-using-BERT","url":"https://github.com/rupakdas18/SemEval-2017-Task-4-A-B-C-using-BERT"},{"title":"hoangtrungchinh/Bert-SQuAD-v2","url":"https://github.com/hoangtrungchinh/Bert-SQuAD-v2"},{"title":"maxmatical/pytorch-projects","url":"https://github.com/maxmatical/pytorch-projects"},{"title":"rupakdas18/Research-Project-UMD-CS-5642","url":"https://github.com/rupakdas18/Research-Project-UMD-CS-5642"},{"title":"moon23k/Scheduled_Sampling","url":"https://github.com/moon23k/Scheduled_Sampling"},{"title":"adi2103/AML-CoVe","url":"https://github.com/adi2103/AML-CoVe"},{"title":"noriyukipy/tfchat","url":"https://github.com/noriyukipy/tfchat"},{"title":"why2000/DuReader-bert","url":"https://github.com/why2000/DuReader-bert"},{"title":"cospplay/bert-master","url":"https://github.com/cospplay/bert-master"},{"title":"frankcgq105/BERTCHEN","url":"https://github.com/frankcgq105/BERTCHEN"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/audio_spectrogram_transformer"},{"title":"ishritam/Image-captioning-with-visual-attention","url":"https://github.com/ishritam/Image-captioning-with-visual-attention"},{"title":"jgcbrouns/Introducing-Sparsity-in-the-Transformer","url":"https://github.com/jgcbrouns/Introducing-Sparsity-in-the-Transformer"},{"title":"scrayish/ML_NLP","url":"https://github.com/scrayish/ML_NLP"},{"title":"goldenbili/bert_lamb_pretrain","url":"https://github.com/goldenbili/bert_lamb_pretrain"},{"title":"xingniu/sockeye","url":"https://github.com/xingniu/sockeye"},{"title":"jeongchanyoung-1234/De-En-NMT","url":"https://github.com/jeongchanyoung-1234/De-En-NMT"},{"title":"benjamintaiwo/Attention","url":"https://github.com/benjamintaiwo/Attention"},{"title":"noriyukipy/tfdlg","url":"https://github.com/noriyukipy/tfdlg"},{"title":"Lemoners/Attention-Is-All-You-Need","url":"https://github.com/Lemoners/Attention-Is-All-You-Need"},{"title":"Maple728/transformer","url":"https://github.com/Maple728/transformer"},{"title":"jmnolte/hccnet","url":"https://github.com/jmnolte/hccnet"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/4/Translation-Invariant/model"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/transformer"},{"title":"moon23k/Transformer_Archs","url":"https://github.com/moon23k/Transformer_Archs"},{"title":"anuscode/nrms","url":"https://github.com/anuscode/nrms"},{"title":"hrbigelow/transformer-aiayn","url":"https://github.com/hrbigelow/transformer-aiayn"},{"title":"satyajitghana/TSAI-DeepNLP-END2.0","url":"https://github.com/satyajitghana/TSAI-DeepNLP-END2.0"},{"title":"shyam-skk/Parallel_CNN_Transfromer","url":"https://github.com/shyam-skk/Parallel_CNN_Transfromer"},{"title":"kriesbeck/masked-language-prediction","url":"https://github.com/kriesbeck/masked-language-prediction"},{"title":"iejMac/ScriptWriter","url":"https://github.com/iejMac/ScriptWriter"},{"title":"SeoroMin/transformer_pytorch_ver2","url":"https://github.com/SeoroMin/transformer_pytorch_ver2"},{"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":"XuhanLiu/Transformer","url":"https://github.com/XuhanLiu/Transformer"},{"title":"khwajawisal/Attention-augmented-Convolutional-Neural-Networks","url":"https://github.com/khwajawisal/Attention-augmented-Convolutional-Neural-Networks"},{"title":"brightmart/bert_original","url":"https://github.com/brightmart/bert_original"},{"title":"Matthewdowney18/Transformer_Dialogue","url":"https://github.com/Matthewdowney18/Transformer_Dialogue"},{"title":"coxy1989/tfmr","url":"https://github.com/coxy1989/tfmr"},{"title":"asultan123/DL_LLC_Prefetching","url":"https://github.com/asultan123/DL_LLC_Prefetching"},{"title":"zipeiyang/DeepSpeechRecognition","url":"https://github.com/zipeiyang/DeepSpeechRecognition"},{"title":"aaronH45/sentimentAnalysis","url":"https://github.com/aaronH45/sentimentAnalysis"},{"title":"tcxdgit/MachineTranslation_t2t","url":"https://github.com/tcxdgit/MachineTranslation_t2t"},{"title":"nietao2/DeepSpeechRecognition","url":"https://github.com/nietao2/DeepSpeechRecognition"},{"title":"MohamedAbdelsalam9/TT-Transformer","url":"https://github.com/MohamedAbdelsalam9/TT-Transformer"},{"title":"Neoanarika/torchexplainer","url":"https://github.com/Neoanarika/torchexplainer"},{"title":"JNUpython/bert","url":"https://github.com/JNUpython/bert"},{"title":"tbmoon/LANL_Earthquake_Prediction","url":"https://github.com/tbmoon/LANL_Earthquake_Prediction"},{"title":"Helsinki-NLP/shared-info","url":"https://github.com/Helsinki-NLP/shared-info"},{"title":"YuanEric88/bert-nlu","url":"https://github.com/YuanEric88/bert-nlu"},{"title":"davidalbertonogueira/NLP-tutorials","url":"https://github.com/davidalbertonogueira/NLP-tutorials"},{"title":"samyakjain0112/Video-denoising_tensorflow-core-api-2.0","url":"https://github.com/samyakjain0112/Video-denoising_tensorflow-core-api-2.0"},{"title":"Misoknisky/Bert-MultiGpu","url":"https://github.com/Misoknisky/Bert-MultiGpu"},{"title":"AndreiMoraru123/Neural-Machine-Translation","url":"https://github.com/AndreiMoraru123/Neural-Machine-Translation"},{"title":"soumik12345/transformer.pytorch","url":"https://github.com/soumik12345/transformer.pytorch"},{"title":"ShwetaBaranwal/Transformer","url":"https://github.com/ShwetaBaranwal/Transformer"},{"title":"text-machine-lab/transformerpy","url":"https://github.com/text-machine-lab/transformerpy"},{"title":"Andrey885/Machine_translation_PyTorch","url":"https://github.com/Andrey885/Machine_translation_PyTorch"},{"title":"lehinevych/SAAN","url":"https://github.com/lehinevych/SAAN"},{"title":"SpikeKing/My-Bert","url":"https://github.com/SpikeKing/My-Bert"},{"title":"pritam1322/Machine-Translation-with-Transformer","url":"https://github.com/pritam1322/Machine-Translation-with-Transformer"},{"title":"harshit158/paper-dots","url":"https://github.com/harshit158/paper-dots"},{"title":"paulskeie/stadnamn","url":"https://github.com/paulskeie/stadnamn"},{"title":"rupakdas18/SuperGlue-tasks-using-BERT","url":"https://github.com/rupakdas18/SuperGlue-tasks-using-BERT"},{"title":"SeoroMin/transformer_pytorch","url":"https://github.com/SeoroMin/transformer_pytorch"},{"title":"christianspybrook/article_recommender","url":"https://github.com/christianspybrook/article_recommender"},{"title":"monimoyd/NLPMachineTranslationUsingTransformer","url":"https://github.com/monimoyd/NLPMachineTranslationUsingTransformer"},{"title":"ngocphucck/BERT-questions-classification","url":"https://github.com/ngocphucck/BERT-questions-classification"},{"title":"Rudedaisy/attention-is-all-you-need-pytorch","url":"https://github.com/Rudedaisy/attention-is-all-you-need-pytorch"},{"title":"seunghwan1228/Transfomer-MachineTranslation","url":"https://github.com/seunghwan1228/Transfomer-MachineTranslation"},{"title":"Harry-Muzart/harry-muzart.github.io","url":"https://github.com/Harry-Muzart/harry-muzart.github.io"},{"title":"KrishnaTarun/Deep-Learning-Lab","url":"https://github.com/KrishnaTarun/Deep-Learning-Lab"},{"title":"thunlp-mt/ckd","url":"https://github.com/thunlp-mt/ckd"},{"title":"plkmo/Transformer-Eng2French","url":"https://github.com/plkmo/Transformer-Eng2French"},{"title":"Nstats/my_bert","url":"https://github.com/Nstats/my_bert"},{"title":"enhuiz/torchnmt","url":"https://github.com/enhuiz/torchnmt"},{"title":"mehdibenamorr/bert-positional-bias-ner","url":"https://github.com/mehdibenamorr/bert-positional-bias-ner"},{"title":"yanqi1811/attention-is-all-you-need","url":"https://github.com/yanqi1811/attention-is-all-you-need"},{"title":"HeshamElAbd/SelfAttentionLangModel","url":"https://github.com/HeshamElAbd/SelfAttentionLangModel"},{"title":"luckynozomi/PPI_Bert","url":"https://github.com/luckynozomi/PPI_Bert"},{"title":"mayurnewase/Quora-Bert","url":"https://github.com/mayurnewase/Quora-Bert"},{"title":"jageshmaharjan/BERT_Service","url":"https://github.com/jageshmaharjan/BERT_Service"},{"title":"moon23k/Transformer_Anchors","url":"https://github.com/moon23k/Transformer_Anchors"},{"title":"junhahyung/bert_finetune","url":"https://github.com/junhahyung/bert_finetune"},{"title":"nicholasbao/nlp_job","url":"https://github.com/nicholasbao/nlp_job"},{"title":"ZmeiGorynych/transformer_pytorch","url":"https://github.com/ZmeiGorynych/transformer_pytorch"},{"title":"majing2019/transformer","url":"https://github.com/majing2019/transformer"},{"title":"flyliu2017/bert_modularized","url":"https://github.com/flyliu2017/bert_modularized"},{"title":"enhuiz/transformer-pytorch","url":"https://github.com/enhuiz/transformer-pytorch"},{"title":"demelin/nematode","url":"https://github.com/demelin/nematode"},{"title":"LoveYang/bert_test","url":"https://github.com/LoveYang/bert_test"},{"title":"littell/NamedTransformer","url":"https://github.com/littell/NamedTransformer"},{"title":"joebluems/Soul_Of_AI","url":"https://github.com/joebluems/Soul_Of_AI"},{"title":"fra-mari/The-Karl-Marx-Press-Review","url":"https://github.com/fra-mari/The-Karl-Marx-Press-Review"},{"title":"microcoder-py/attn-is-all-you-need","url":"https://github.com/microcoder-py/attn-is-all-you-need"},{"title":"binhetech/bert-application","url":"https://github.com/binhetech/bert-application"},{"title":"Chonwai/Learning_BERT","url":"https://github.com/Chonwai/Learning_BERT"},{"title":"EuphoriaYan/bert_component","url":"https://github.com/EuphoriaYan/bert_component"},{"title":"shaikhzhas/bert","url":"https://github.com/shaikhzhas/bert"},{"title":"walkacross/transformer-pytorch","url":"https://github.com/walkacross/transformer-pytorch"},{"title":"appcoreopc/berty","url":"https://github.com/appcoreopc/berty"},{"title":"goldenbili/Bert_Test3","url":"https://github.com/goldenbili/Bert_Test3"},{"title":"Nstats/bert_senti_analysis_ch","url":"https://github.com/Nstats/bert_senti_analysis_ch"},{"title":"Pezhin/best_yelp_review_project_ever","url":"https://github.com/Pezhin/best_yelp_review_project_ever"},{"title":"sauram/Machine-Translation-using-Attention-Model","url":"https://github.com/sauram/Machine-Translation-using-Attention-Model"},{"title":"coco60/bert-test","url":"https://github.com/coco60/bert-test"},{"title":"xbtlin/All-about-Machine-Learning","url":"https://github.com/xbtlin/All-about-Machine-Learning"},{"title":"neburseni/NLP","url":"https://github.com/neburseni/NLP"},{"title":"nrc-cnrc/sockeye-multisource","url":"https://github.com/nrc-cnrc/sockeye-multisource"},{"title":"a414351664/Bert_MRC","url":"https://github.com/a414351664/Bert_MRC"},{"title":"vishnuanil122/Bert-Binary-Text-Classifier","url":"https://github.com/vishnuanil122/Bert-Binary-Text-Classifier"},{"title":"socc-io/piqaboo","url":"https://github.com/socc-io/piqaboo"},{"title":"meizi1114/bert","url":"https://github.com/meizi1114/bert"},{"title":"nmfisher/bert-modified","url":"https://github.com/nmfisher/bert-modified"},{"title":"DJJune/Transformer","url":"https://github.com/DJJune/Transformer"},{"title":"lennonzurich/lalala","url":"https://github.com/lennonzurich/lalala"},{"title":"s9891326/Fine-Tuning-BERT","url":"https://github.com/s9891326/Fine-Tuning-BERT"},{"title":"monimoyd/NLPEnglishToPythonCodeUsingTransformer","url":"https://github.com/monimoyd/NLPEnglishToPythonCodeUsingTransformer"},{"title":"niccolot/ENG-ITA_NMT","url":"https://github.com/niccolot/ENG-ITA_NMT"},{"title":"Aveek-Saha/Transformer","url":"https://github.com/Aveek-Saha/Transformer"},{"title":"jaisenbe58r/NLP-Transformer_Translator","url":"https://github.com/jaisenbe58r/NLP-Transformer_Translator"},{"title":"EmilioTyl/transformers_from_scratch","url":"https://github.com/EmilioTyl/transformers_from_scratch"},{"title":"fstahlberg/tensor2tensor","url":"https://github.com/fstahlberg/tensor2tensor"},{"title":"Katsumata420/bert_mlm","url":"https://github.com/Katsumata420/bert_mlm"},{"title":"Chinnu1103/Machine-Translation-using-Transformers","url":"https://github.com/Chinnu1103/Machine-Translation-using-Transformers"},{"title":"ricardordb/bert","url":"https://github.com/ricardordb/bert"},{"title":"tomdyer10/fake_news","url":"https://github.com/tomdyer10/fake_news"},{"title":"vanslerry/long_text","url":"https://github.com/vanslerry/long_text"},{"title":"emanuele-progr/PSSP","url":"https://github.com/emanuele-progr/PSSP"},{"title":"wchh127/yykf","url":"https://github.com/wchh127/yykf"},{"title":"krantirk/BERT-Pretrained-model","url":"https://github.com/krantirk/BERT-Pretrained-model"},{"title":"vanpersie32/Multigpu-Bert","url":"https://github.com/vanpersie32/Multigpu-Bert"},{"title":"nlinc1905/dsilt-tsa","url":"https://github.com/nlinc1905/dsilt-tsa"},{"title":"h4ste/oscar","url":"https://github.com/h4ste/oscar"},{"title":"bartzi/chainer-transformer","url":"https://github.com/bartzi/chainer-transformer"},{"title":"franknb/Text-Summarization","url":"https://github.com/franknb/Text-Summarization"},{"title":"shahrukhx01/ocr-test","url":"https://github.com/shahrukhx01/ocr-test"},{"title":"MashaKubyshina/learning_ML","url":"https://github.com/MashaKubyshina/learning_ML"},{"title":"JanAthmer/Compositional-generalization-capabillity-of-Transformer","url":"https://github.com/JanAthmer/Compositional-generalization-capabillity-of-Transformer"},{"title":"vikashranjan/transformer","url":"https://github.com/vikashranjan/transformer"},{"title":"shreyash8/English_to_Hindi_NMT","url":"https://github.com/shreyash8/English_to_Hindi_NMT"},{"title":"mhamedLmarbouh/Attention-is-all-you-need","url":"https://github.com/mhamedLmarbouh/Attention-is-all-you-need"},{"title":"tree-park/transformer_lm","url":"https://github.com/tree-park/transformer_lm"},{"title":"BasileBron/Artificial-Intelligence-Lexical","url":"https://github.com/BasileBron/Artificial-Intelligence-Lexical"},{"title":"basile-bron/Artificial-Intelligence-Lexical","url":"https://github.com/basile-bron/Artificial-Intelligence-Lexical"},{"title":"EugeneSel/EUMT","url":"https://github.com/EugeneSel/EUMT"},{"title":"Fuchai/language","url":"https://github.com/Fuchai/language"},{"title":"flyliu2017/bert","url":"https://github.com/flyliu2017/bert"},{"title":"kotu931226/classifier_transformer_pytorch","url":"https://github.com/kotu931226/classifier_transformer_pytorch"},{"title":"rasbot/plot-bot","url":"https://github.com/rasbot/plot-bot"},{"title":"alililia/ms_contrib","url":"https://github.com/alililia/ms_contrib/tree/main/ascend_transformer"},{"title":"alililia/ms_contrib","url":"https://github.com/alililia/ms_contrib/tree/main/gpu_transformer"},{"title":"alimpiev/embeddings_persistent_homology","url":"https://github.com/alimpiev/embeddings_persistent_homology"},{"title":"mehdibenamorr/Token-Positional-Bias","url":"https://github.com/mehdibenamorr/Token-Positional-Bias"},{"title":"ololo123321/maestro","url":"https://github.com/ololo123321/maestro"},{"title":"pengshuyuan/Bert","url":"https://github.com/pengshuyuan/Bert"},{"title":"Kevin-Vora/bert-embedding-gluonnlp-edit-","url":"https://github.com/Kevin-Vora/bert-embedding-gluonnlp-edit-"},{"title":"icewing1996/bert_dep","url":"https://github.com/icewing1996/bert_dep"},{"title":"Gaozhen0816/BERT_QA_for_Chinese","url":"https://github.com/Gaozhen0816/BERT_QA_for_Chinese"},{"title":"FengJiaChunFromSYSU/Bert","url":"https://github.com/FengJiaChunFromSYSU/Bert"},{"title":"Nimesh-Patel/BERT","url":"https://github.com/Nimesh-Patel/BERT"},{"title":"souvikshanku/translit-former","url":"https://github.com/souvikshanku/translit-former"},{"title":"chrisleunglokhin/Capstone-BERT","url":"https://github.com/chrisleunglokhin/Capstone-BERT"},{"title":"Nstats/bert_MRC","url":"https://github.com/Nstats/bert_MRC"},{"title":"maxudong1993/mybert","url":"https://github.com/maxudong1993/mybert"},{"title":"faizansuhail89/bert","url":"https://github.com/faizansuhail89/bert"},{"title":"ykrmm/TREMBA","url":"https://github.com/ykrmm/TREMBA"},{"title":"goldenbili/Bert_Test2","url":"https://github.com/goldenbili/Bert_Test2"},{"title":"AtluriNikhil/Image-Captioning","url":"https://github.com/AtluriNikhil/Image-Captioning"},{"title":"anhinga/JuliaCon2021-poster","url":"https://github.com/anhinga/JuliaCon2021-poster"},{"title":"lidongliang666/cv_deep_learning","url":"https://github.com/lidongliang666/cv_deep_learning"},{"title":"zankner/Transformer","url":"https://github.com/zankner/Transformer"},{"title":"rohan400/PepperQA","url":"https://github.com/rohan400/PepperQA"},{"title":"tyxr/bert","url":"https://github.com/tyxr/bert"},{"title":"extensive-nlp/TSAI-DeepNLP-END2.0","url":"https://github.com/extensive-nlp/TSAI-DeepNLP-END2.0"},{"title":"ykrmm/ICLR_2020","url":"https://github.com/ykrmm/ICLR_2020"},{"title":"joytianya/google_bert","url":"https://github.com/joytianya/google_bert"},{"title":"Zehui127/SQUAD_BERT","url":"https://github.com/Zehui127/SQUAD_BERT"},{"title":"Shinya-Kouda/kgc","url":"https://github.com/Shinya-Kouda/kgc"},{"title":"algharak/BERTenhance","url":"https://github.com/algharak/BERTenhance"},{"title":"coronazap/bert_client","url":"https://github.com/coronazap/bert_client"},{"title":"saurabhnlp/bert","url":"https://github.com/saurabhnlp/bert"},{"title":"TSLNIHAOGIT/bert","url":"https://github.com/TSLNIHAOGIT/bert"},{"title":"Maz101/pretrainingdataset","url":"https://github.com/Maz101/pretrainingdataset"},{"title":"sarthaxxxxx/Attention-is-all-you-need","url":"https://github.com/sarthaxxxxx/Attention-is-all-you-need"},{"title":"shao-chi/ImageCaption","url":"https://github.com/shao-chi/ImageCaption"},{"title":"MOHAMEDELDAKDOUKY/bert_adjusted","url":"https://github.com/MOHAMEDELDAKDOUKY/bert_adjusted"},{"title":"Rami97rgb/French-to-English-Translator","url":"https://github.com/Rami97rgb/French-to-English-Translator"},{"title":"tree-park/kor-to-eng-translation","url":"https://github.com/tree-park/kor-to-eng-translation"},{"title":"G-4-R-Y/Tweet-Sentiment-Extraction-roBERTa-5fold","url":"https://github.com/G-4-R-Y/Tweet-Sentiment-Extraction-roBERTa-5fold"},{"title":"goodluck4s/bert-","url":"https://github.com/goodluck4s/bert-"},{"title":"pingheng001/Cnn-Bert","url":"https://github.com/pingheng001/Cnn-Bert"},{"title":"abmitra84/Machine_Translation","url":"https://github.com/abmitra84/Machine_Translation"},{"title":"leehyunjun-seoultech/seoultech","url":"https://github.com/leehyunjun-seoultech/seoultech"},{"title":"lif31up/extended-BERT-for-low-rank-adaption","url":"https://github.com/lif31up/extended-BERT-for-low-rank-adaption"},{"title":"xiaopp123/bert_explain","url":"https://github.com/xiaopp123/bert_explain"},{"title":"anishnarkar/experiments_deeplearning_models","url":"https://github.com/anishnarkar/experiments_deeplearning_models"},{"title":"owainwest/uniprot_bert","url":"https://github.com/owainwest/uniprot_bert"},{"title":"shouvikcirca/Transformer_MiniProject","url":"https://github.com/shouvikcirca/Transformer_MiniProject"},{"title":"xitianxiaofeixue/BERT","url":"https://github.com/xitianxiaofeixue/BERT"},{"title":"mitran27/Attention-is-all-you-Need","url":"https://github.com/mitran27/Attention-is-all-you-Need"},{"title":"MindSpore-scientific/code-8","url":"https://github.com/MindSpore-scientific/code-8/tree/main/Translation-Invariant/model"},{"title":"cuber2460/bert","url":"https://github.com/cuber2460/bert"},{"title":"caoyujiALgLM/NLP-progress","url":"https://github.com/caoyujiALgLM/NLP-progress"},{"title":"longbowking/bert","url":"https://github.com/longbowking/bert"},{"title":"AssafSinger94/sigmorphon-2020-inflection","url":"https://github.com/AssafSinger94/sigmorphon-2020-inflection"},{"title":"cloudmcloudyo/capstone","url":"https://github.com/cloudmcloudyo/capstone"},{"title":"semicontinuity/nlp","url":"https://github.com/semicontinuity/nlp"},{"title":"mithunpaul08/bert_tensorflow","url":"https://github.com/mithunpaul08/bert_tensorflow"},{"title":"DeligientSloth/QQsim","url":"https://github.com/DeligientSloth/QQsim"},{"title":"G-4-R-Y/Tweet-Sentiment-Extraction","url":"https://github.com/G-4-R-Y/Tweet-Sentiment-Extraction"},{"title":"xesdiny/test-bert-master","url":"https://github.com/xesdiny/test-bert-master"},{"title":"lif31up/attention-is-all-you-need","url":"https://github.com/lif31up/attention-is-all-you-need"},{"title":"SCismycat/bert_code_view","url":"https://github.com/SCismycat/bert_code_view"},{"title":"DanieleVeri/deep_comedy","url":"https://github.com/DanieleVeri/deep_comedy"},{"title":"karenacorn99/explore-bert","url":"https://github.com/karenacorn99/explore-bert"},{"title":"AlCorreia/FABIR","url":"https://github.com/AlCorreia/FABIR"},{"title":"shuaishuaij/Machine-Translation","url":"https://github.com/shuaishuaij/Machine-Translation"},{"title":"StoneGH/bert","url":"https://github.com/StoneGH/bert"},{"title":"keiyamashita111/aaproject","url":"https://github.com/keiyamashita111/aaproject"},{"title":"JeheonPark596/sentimentsurvival","url":"https://github.com/JeheonPark596/sentimentsurvival"},{"title":"camlaedtke/NLP","url":"https://github.com/camlaedtke/NLP"},{"title":"cadia-lvl/fastspeech2","url":"https://github.com/cadia-lvl/fastspeech2"},{"title":"Xinsen-Zhang/transformer","url":"https://github.com/Xinsen-Zhang/transformer"},{"title":"haidershaour/bert","url":"https://github.com/haidershaour/bert"},{"title":"yeeeqichen/Bert","url":"https://github.com/yeeeqichen/Bert"},{"title":"Maz101/Bert","url":"https://github.com/Maz101/Bert"},{"title":"thecodemasterk/BERT","url":"https://github.com/thecodemasterk/BERT"},{"title":"rishavbhurtel/sentiment-classifier","url":"https://github.com/rishavbhurtel/sentiment-classifier"},{"title":"xuzhezhaozhao/bert_reading","url":"https://github.com/xuzhezhaozhao/bert_reading"},{"title":"dzqjorking/transpose","url":"https://github.com/dzqjorking/transpose"},{"title":"Arthurizijar/Bert_Airport","url":"https://github.com/Arthurizijar/Bert_Airport"},{"title":"nachiketaa/bert","url":"https://github.com/nachiketaa/bert"},{"title":"Joshuaoneheart/Fintech-Final-Report","url":"https://github.com/Joshuaoneheart/Fintech-Final-Report"},{"title":"paolanu/BERT_epitope","url":"https://github.com/paolanu/BERT_epitope"},{"title":"penny9287/sockeye","url":"https://github.com/penny9287/sockeye"},{"title":"shouvikcirca/Transformer","url":"https://github.com/shouvikcirca/Transformer"},{"title":"gavincaoyuji/NLP","url":"https://github.com/gavincaoyuji/NLP"},{"title":"zhangbo2008/best_pytorch_transformer","url":"https://github.com/zhangbo2008/best_pytorch_transformer"},{"title":"XINZXZHANG/Bert_repo","url":"https://github.com/XINZXZHANG/Bert_repo"},{"title":"yuhangT/tf_bert","url":"https://github.com/yuhangT/tf_bert"},{"title":"eunseo1092/Graduation_project","url":"https://github.com/eunseo1092/Graduation_project"},{"title":"Amy-1114/transformer","url":"https://github.com/Amy-1114/transformer"},{"title":"DeligientSloth/bert-tensorflow","url":"https://github.com/DeligientSloth/bert-tensorflow"},{"title":"Kirankumaraswamy/Transformers","url":"https://github.com/Kirankumaraswamy/Transformers"},{"title":"Walter-B/bert-20-classes","url":"https://github.com/Walter-B/bert-20-classes"},{"title":"chandu7077/mybert","url":"https://github.com/chandu7077/mybert"},{"title":"ahsanabbas123/Transformer","url":"https://github.com/ahsanabbas123/Transformer"},{"title":"halo090770/bert","url":"https://github.com/halo090770/bert"},{"title":"rickyHong/Google-BERT-repl","url":"https://github.com/rickyHong/Google-BERT-repl"},{"title":"llx666/git_demo","url":"https://github.com/llx666/git_demo"},{"title":"TonyX19/bert_hyperpartisan","url":"https://github.com/TonyX19/bert_hyperpartisan"},{"title":"Caesarzhang/bert-zh","url":"https://github.com/Caesarzhang/bert-zh"},{"title":"Yipeng91/text_classifier_pub","url":"https://github.com/Yipeng91/text_classifier_pub"},{"title":"leejieun51/transformer","url":"https://github.com/leejieun51/transformer"},{"title":"Khalid-Jamal/annotated-transformer-Arabic","url":"https://github.com/Khalid-Jamal/annotated-transformer-Arabic"},{"title":"chalothon/BERT_Practice","url":"https://github.com/chalothon/BERT_Practice"},{"title":"EthanWYB/bert-classification","url":"https://github.com/EthanWYB/bert-classification"},{"title":"Shasvat-Desai/Shasvat-Desai","url":"https://github.com/Shasvat-Desai/Shasvat-Desai"},{"title":"Osobarako/alduswarrensewell","url":"https://github.com/Osobarako/alduswarrensewell"},{"title":"Charliesgithub20221030/BERT","url":"https://github.com/Charliesgithub20221030/BERT"},{"title":"IrishCoffee/cudnnMultiHeadAttention","url":"https://github.com/IrishCoffee/cudnnMultiHeadAttention"},{"title":"guzhang480/Google_BERT","url":"https://github.com/guzhang480/Google_BERT"},{"title":"zsweet/BERT_zsw","url":"https://github.com/zsweet/BERT_zsw"},{"title":"mayoor/attention_network_experiments","url":"https://github.com/mayoor/attention_network_experiments"},{"title":"1wy/bert","url":"https://github.com/1wy/bert"},{"title":"Izecson/sockeye-1.16.6","url":"https://github.com/Izecson/sockeye-1.16.6"},{"title":"2023-MindSpore-1/ms-code-14","url":"https://github.com/2023-MindSpore-1/ms-code-14/tree/main/Transformer"},{"title":"lenacabrera/gb_mnmt","url":"https://github.com/lenacabrera/gb_mnmt"},{"title":"zapplea/bert","url":"https://github.com/zapplea/bert"},{"title":"sherinaseri/bert","url":"https://github.com/sherinaseri/bert"},{"title":"OPAYA/Transformer","url":"https://github.com/OPAYA/Transformer"},{"title":"ramanakshay/transformer","url":"https://github.com/ramanakshay/transformer"},{"title":"jinzhenfan/BERT","url":"https://github.com/jinzhenfan/BERT"},{"title":"derylucio/Transformer","url":"https://github.com/derylucio/Transformer"},{"title":"anhtu293/transformer_from_scratch","url":"https://github.com/anhtu293/transformer_from_scratch"},{"title":"jangjoongkeon/JK","url":"https://github.com/jangjoongkeon/JK"},{"title":"chen-xiong-yi/OwnBERT","url":"https://github.com/chen-xiong-yi/OwnBERT"},{"title":"HanhaiNotHai/transformer","url":"https://github.com/HanhaiNotHai/transformer"},{"title":"antoinecollas/transformer_neural_machine_translation","url":"https://github.com/antoinecollas/transformer_neural_machine_translation"},{"title":"DeokO/bert-excercise-ongoing","url":"https://github.com/DeokO/bert-excercise-ongoing"},{"title":"svakulenk0/response_eval","url":"https://github.com/svakulenk0/response_eval"},{"title":"fciannel/bert_fciannel","url":"https://github.com/fciannel/bert_fciannel"},{"title":"yydai/bert_test","url":"https://github.com/yydai/bert_test"},{"title":"Satan012/BERT","url":"https://github.com/Satan012/BERT"},{"title":"VedantYadav/Transformer","url":"https://github.com/VedantYadav/Transformer"},{"title":"kiko441500/google_bert","url":"https://github.com/kiko441500/google_bert"},{"title":"rpuiggari/bert2","url":"https://github.com/rpuiggari/bert2"},{"title":"tvinith/bert","url":"https://github.com/tvinith/bert"},{"title":"yoongtr/Grammar-Error-Correction-with-OpenNMT-tf","url":"https://github.com/yoongtr/Grammar-Error-Correction-with-OpenNMT-tf"},{"title":"magahub/songrnn","url":"https://github.com/magahub/songrnn"},{"title":"wayalhruhi/gogle_bert","url":"https://github.com/wayalhruhi/gogle_bert"},{"title":"RenXiangyuan/tf_bert","url":"https://github.com/RenXiangyuan/tf_bert"},{"title":"vijay120/bert","url":"https://github.com/vijay120/bert"},{"title":"wangmz15/Chinese-Error-Correction-with-THUMT","url":"https://github.com/wangmz15/Chinese-Error-Correction-with-THUMT"},{"title":"anirudharc/transformer","url":"https://github.com/anirudharc/transformer"},{"title":"2023-MindSpore-4/Code8","url":"https://github.com/2023-MindSpore-4/Code8/tree/main/AttentionCluster"},{"title":"abhiagg92/bert_sentiment","url":"https://github.com/abhiagg92/bert_sentiment"},{"title":"XUJitao/WordEmbedding","url":"https://github.com/XUJitao/WordEmbedding"},{"title":"yueyongjiao/attention_is_all_you_need_pytorch","url":"https://github.com/yueyongjiao/attention_is_all_you_need_pytorch"},{"title":"saurabhkulkarni77/BERT_multilabel","url":"https://github.com/saurabhkulkarni77/BERT_multilabel"},{"title":"zhang-huihui/git-repository","url":"https://github.com/zhang-huihui/git-repository"},{"title":"bshantam97/Attention_Based_Networks","url":"https://github.com/bshantam97/Attention_Based_Networks"},{"title":"FaskyCC/TextClassification","url":"https://github.com/FaskyCC/TextClassification"},{"title":"yiyc-kor/bert-study","url":"https://github.com/yiyc-kor/bert-study"},{"title":"liqichen6688/duo-attention","url":"https://github.com/liqichen6688/duo-attention"},{"title":"mayurnewase/Translation","url":"https://github.com/mayurnewase/Translation"},{"title":"bhavitvyamalik/bert","url":"https://github.com/bhavitvyamalik/bert"},{"title":"TSLNIHAOGIT/bert_run","url":"https://github.com/TSLNIHAOGIT/bert_run"},{"title":"idiotprofessorchen/bert.github.io","url":"https://github.com/idiotprofessorchen/bert.github.io"},{"title":"junhahyung/bert_transfer","url":"https://github.com/junhahyung/bert_transfer"},{"title":"drumpt/Transformer","url":"https://github.com/drumpt/Transformer"},{"title":"StevenLai1994/AM_and_LM","url":"https://github.com/StevenLai1994/AM_and_LM"},{"title":"MindSpore-scientific/code-11","url":"https://github.com/MindSpore-scientific/code-11/tree/main/Translation-Invariant/model"},{"title":"eleanorye00/Gamifier","url":"https://github.com/eleanorye00/Gamifier"},{"title":"bluejurand/Kaggle_QA_Google_Labeling","url":"https://github.com/bluejurand/Kaggle_QA_Google_Labeling"},{"title":"YYGXjpg/BERT_WL","url":"https://github.com/YYGXjpg/BERT_WL"},{"title":"ZurichNLP/sockeye","url":"https://github.com/ZurichNLP/sockeye"},{"title":"JohannLee1996/bert","url":"https://github.com/JohannLee1996/bert"},{"title":"insigh/THUMT","url":"https://github.com/insigh/THUMT"},{"title":"jamesdvance/predicting_clicks","url":"https://github.com/jamesdvance/predicting_clicks"},{"title":"Gaozhen0816/BERT_QA_For_AILaw","url":"https://github.com/Gaozhen0816/BERT_QA_For_AILaw"},{"title":"myamamoto555/tf-bert","url":"https://github.com/myamamoto555/tf-bert"},{"title":"yueyongjiao/Transformer-Contextual","url":"https://github.com/yueyongjiao/Transformer-Contextual"},{"title":"natel9178/transformer-refork","url":"https://github.com/natel9178/transformer-refork"},{"title":"dl-nlp/dl-nlp.github.io","url":"https://github.com/dl-nlp/dl-nlp.github.io"},{"title":"TYTYTYTYTYTYTYTYTY/558-project","url":"https://github.com/TYTYTYTYTYTYTYTYTY/558-project"},{"title":"mhaseeb123/DeepMSim","url":"https://github.com/mhaseeb123/DeepMSim"},{"title":"nvshrao/Bidirectional-Transformer","url":"https://github.com/nvshrao/Bidirectional-Transformer"},{"title":"feizc/Machine-Translation-Pytorch","url":"https://github.com/feizc/Machine-Translation-Pytorch"},{"title":"tcnguyen/bert","url":"https://github.com/tcnguyen/bert"},{"title":"tjrwlgns1198/ChatBot","url":"https://github.com/tjrwlgns1198/ChatBot"},{"title":"yumoh/speech-keras","url":"https://github.com/yumoh/speech-keras"},{"title":"semal/bert","url":"https://github.com/semal/bert"},{"title":"caoyujiALgLM/NLP","url":"https://github.com/caoyujiALgLM/NLP"},{"title":"giagia96/DeepComedy","url":"https://github.com/giagia96/DeepComedy"},{"title":"thanhlong1997/bert_quora","url":"https://github.com/thanhlong1997/bert_quora"},{"title":"cosmoquester/seq2seq","url":"https://github.com/cosmoquester/seq2seq"},{"title":"lovedavidsilva/bert_old_version","url":"https://github.com/lovedavidsilva/bert_old_version"},{"title":"gggggeun/DeepLearning_Architecture","url":"https://github.com/gggggeun/DeepLearning_Architecture"},{"title":"Wolfie8935/Implementation-of-Attention-is-all-you-need","url":"https://github.com/Wolfie8935/Implementation-of-Attention-is-all-you-need"},{"title":"kingcheng2000/bert","url":"https://github.com/kingcheng2000/bert"},{"title":"sonrisa07/transformer","url":"https://github.com/sonrisa07/transformer"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52456,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"USSM + Supervised DeepNet + KB","metrics":{"Accuracy":"52.8"},"paper_url":"https://arxiv.org/abs/1905.13497v1","paper_title":"Attention Is (not) All You Need for Commonsense Reasoning","paper_date":"2019-05-31","code_links":[{"title":"SAP-samples/acl2020-commonsense","url":"https://github.com/SAP-samples/acl2020-commonsense"},{"title":"SAP-samples/acl2019-commonsense-reasoning","url":"https://github.com/SAP-samples/acl2019-commonsense-reasoning"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52457,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"KEE+NKAM on WinoGrande","metrics":{"Accuracy":"52.8"},"paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","paper_date":"2019-07-24","code_links":[{"title":"vered1986/self_talk","url":"https://github.com/vered1986/self_talk"},{"title":"mindspore-ai/contrib","url":"https://github.com/mindspore-ai/contrib/tree/master/application/WinoGrande"},{"title":"swarnahub/explanationhardness","url":"https://github.com/swarnahub/explanationhardness"},{"title":"crherlihy/clinical_nli_artifacts","url":"https://github.com/crherlihy/clinical_nli_artifacts"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/4/WinoGrande"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/3/WinoGrande"},{"title":"MindCode-4/code-13","url":"https://github.com/MindCode-4/code-13/tree/main/WinoGrande"},{"title":"MindSpore-scientific/code-5","url":"https://github.com/MindSpore-scientific/code-5/tree/main/WinoGrande"},{"title":"MindSpore-scientific/code-14","url":"https://github.com/MindSpore-scientific/code-14/tree/main/WinoGrande"},{"title":"MindSpore-scientific-2/code-3","url":"https://github.com/MindSpore-scientific-2/code-3/tree/main/WinoGrande"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52458,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"USSM + KB","metrics":{"Accuracy":"52"},"paper_url":"https://arxiv.org/abs/1905.13497v1","paper_title":"Attention Is (not) All You Need for Commonsense Reasoning","paper_date":"2019-05-31","code_links":[{"title":"SAP-samples/acl2020-commonsense","url":"https://github.com/SAP-samples/acl2020-commonsense"},{"title":"SAP-samples/acl2019-commonsense-reasoning","url":"https://github.com/SAP-samples/acl2019-commonsense-reasoning"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52459,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Random chance baseline","metrics":{"Accuracy":"50"},"paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","paper_date":"2021-04-16","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52460,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Hybrid H3 125M (3-shot, logit scoring)","metrics":{"Accuracy":"43.3"},"paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","paper_date":"2022-12-28","code_links":[{"title":"hazyresearch/safari","url":"https://github.com/hazyresearch/safari"},{"title":"hazyresearch/h3","url":"https://github.com/hazyresearch/h3"},{"title":"lindermanlab/S5","url":"https://github.com/lindermanlab/S5"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52461,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Pythia 2.8B (0-shot)","metrics":{"Accuracy":"38.5"},"paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","paper_date":"2023-04-03","code_links":[{"title":"Lightning-AI/lit-gpt","url":"https://github.com/Lightning-AI/lit-gpt"},{"title":"jzhang38/tinyllama","url":"https://github.com/jzhang38/tinyllama"},{"title":"eleutherai/gpt-neox","url":"https://github.com/eleutherai/gpt-neox"},{"title":"eleutherai/pythia","url":"https://github.com/eleutherai/pythia"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52462,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Neo-6B (few-shot)","metrics":{"Accuracy":"36.5"},"paper_url":"https://arxiv.org/abs/2210.02441v3","paper_title":"Ask Me Anything: A simple strategy for prompting language models","paper_date":"2022-10-05","code_links":[{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"simran-arora/privacy_fm","url":"https://github.com/simran-arora/privacy_fm"},{"title":"simran-arora/focus","url":"https://github.com/simran-arora/focus"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52463,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Pythia 6.9B (0-shot)","metrics":{"Accuracy":"36.5"},"paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","paper_date":"2023-04-03","code_links":[{"title":"Lightning-AI/lit-gpt","url":"https://github.com/Lightning-AI/lit-gpt"},{"title":"jzhang38/tinyllama","url":"https://github.com/jzhang38/tinyllama"},{"title":"eleutherai/gpt-neox","url":"https://github.com/eleutherai/gpt-neox"},{"title":"eleutherai/pythia","url":"https://github.com/eleutherai/pythia"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52464,"task":"Coreference Resolution","parent_task":null,"dataset":"Winograd Schema Challenge","model_name":"Pythia 12B (5-shot)","metrics":{"Accuracy":"36.5"},"paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","paper_date":"2023-04-03","code_links":[{"title":"Lightning-AI/lit-gpt","url":"https://github.com/Lightning-AI/lit-gpt"},{"title":"jzhang38/tinyllama","url":"https://github.com/jzhang38/tinyllama"},{"title":"eleutherai/gpt-neox","url":"https://github.com/eleutherai/gpt-neox"},{"title":"eleutherai/pythia","url":"https://github.com/eleutherai/pythia"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}