paper-with-me

Sentiment Analysis 벤치마크

Sentiment Analysis on SST-2 Binary classification

87개 결과 · ⬇ CSV · JSON

Accuracy

54.72 65.41 76.11 86.81 97.5 2013-10 2026-09 MV-RNN — 82.9 (2013-10-01) CNN-multichannel [kim2013] — 88.1 (2014-08-25) Consistency Tree LSTM with tuned Glove vectors [tai2015improved] — 88.0 (2015-02-28) 2-layer LSTM [tai2015improved] — 86.3 (2015-02-28) DMN [ankit16] — 88.6 (2015-06-24) C-LSTM — 87.8 (2015-11-27) CNN + Logic rules — 89.3 (2016-03-21) Neural Semantic Encoder — 89.7 (2016-07-14) BLSTM-2DCNN — 89.5 (2016-11-21) bmLSTM — 91.8 (2017-04-05) CNN — 91.2 (2017-07-06) BCN+Char+CoVe — 90.3 (2017-08-01) Joined Model Multi-tasking — 54.72 (2017-08-01) Block-sparse LSTM — 93.2 (2017-12-01) USE_T+CNN (lrn w.e.) — 87.21 (2018-03-29) Capsule-B — 86.8 (2018-03-29) byte mLSTM7 — 91.7 (2018-05-14) Suffix BiLSTM — 91.2 (2018-05-18) SWEM-concat — 84.3 (2018-05-24) Standard DR-AGG — 87.6 (2018-06-05) Reverse DR-AGG — 87.2 (2018-06-05) DC-MCNN — 86.99 (2018-07-01) ToWE-CBOW — 78.8 (2018-08-01) CNN-RNF-LSTM — 90.0 (2018-08-28) Bi-CAS-LSTM — 91.3 (2018-09-07) GloVe+Emo2Vec — 82.3 (2018-09-12) Emo2Vec — 81.2 (2018-09-12) Snorkel MeTaL(ensemble) — 96.2 (2018-10-05) BERT-LARGE — 94.9 (2018-10-11) Transformer (finetune) — 90.9 (2018-12-04) MT-DNN — 95.6 (2019-01-31) CNN Large — 94.6 (2019-03-19) Single layer bilstm distilled from BERT — 90.7 (2019-03-28) MT-DNN-ensemble — 96.5 (2019-04-20) ERNIE — 93.5 (2019-05-17) STM+TSED+PT+2L — 86.95 (2019-05-31) XLNet (single model) — 97.0 (2019-06-19) XLNet-Large (ensemble) — 96.8 (2019-06-19) SpanBERT — 94.8 (2019-07-24) RoBERTa (ensemble) — 96.7 (2019-07-26) ERNIE 2.0 Base — 95.0 (2019-07-29) StructBERTRoBERTa ensemble — 97.1 (2019-08-13) MPAD-path — 87.75 (2019-08-17) Q-BERT (Shen et al., 2020) — 94.8 (2019-09-12) TinyBERT-6 67M — 93.1 (2019-09-23) TinyBERT-4 14.5M — 92.6 (2019-09-23) ALBERT — 97.1 (2019-09-26) DistilBERT 66M — 91.3 (2019-10-02) BERT Base — 91.2 (2019-10-04) Q8BERT (Zafrir et al., 2019) — 94.7 (2019-10-14) T5-11B — 97.5 (2019-10-23) T5-3B — 97.4 (2019-10-23) T5-Large 770M — 96.3 (2019-10-23) T5-Base — 95.2 (2019-10-23) T5-Small — 91.8 (2019-10-23) Heinsen Routing + GPT-2 — 95.6 (2019-11-02) MT-DNN-SMART — 97.5 (2019-11-08) MT-DNN — 93.6 (2019-11-08) SMART+BERT-BASE — 93.0 (2019-11-08) FLOATER-large — 96.7 (2020-03-13) ELECTRA — 96.9 (2020-03-23) DeBERTa (large) — 96.5 (2020-06-05) SqueezeBERT — 91.4 (2020-06-19) BigBird — 94.6 (2020-07-28) PAR BERT Base — 91.6 (2020-09-09) PSQ (Chen et al., 2020) — 96.2 (2020-10-27) RealFormer — 94.04 (2020-12-21) MLM+ del-word+ reorder — 94.5 (2020-12-31) MUPPET Roberta Large — 97.4 (2021-01-26) MUPPET Roberta base — 96.7 (2021-01-26) Nyströmformer — 91.4 (2021-02-07) 24hBERT — 93.0 (2021-04-15) RoBERTa-large 355M + Entailment as Few-shot Learner — 96.9 (2021-04-29) FNet-Large — 94.0 (2021-05-09) gMLP-large — 94.8 (2021-05-17) Charformer-Base — 91.6 (2021-06-23) RoBERTa+DualCL — 94.91 (2022-01-21) ASA + RoBERTa — 96.3 (2022-06-25) ASA + BERT-base — 94.1 (2022-06-25) RoBERTa-large 355M (MLP quantized vector-wise, fine-tuned) — 96.4 (2022-08-15) Heinsen Routing + RoBERTa-large — 96.0 (2022-11-20) LM-CPPF RoBERTa-base — 93.2 (2023-05-29) RoBERTa + SubRegWeigh (K-means) — 94.84 (2024-09-10) MV-RNN — 82.9 (2013-10-01) CNN-multichannel [kim2013] — 88.1 (2014-08-25) DMN [ankit16] — 88.6 (2015-06-24) CNN + Logic rules — 89.3 (2016-03-21) Neural Semantic Encoder — 89.7 (2016-07-14) bmLSTM — 91.8 (2017-04-05) Block-sparse LSTM — 93.2 (2017-12-01) Snorkel MeTaL(ensemble) — 96.2 (2018-10-05) MT-DNN-ensemble — 96.5 (2019-04-20) XLNet (single model) — 97.0 (2019-06-19) StructBERTRoBERTa ensemble — 97.1 (2019-08-13) T5-11B — 97.5 (2019-10-23)
RankModel AccuracyDev AccuracyAttack Success Rate PaperCodeYear
1 T5-11B 97.5–– Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer huggingface/transformers · PaddlePaddle/PaddleNLP · google-research/text-to-text-transfer-transformer · +54 2019
1 MT-DNN-SMART 97.5–– SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization namisan/mt-dnn · microsoft/MT-DNN · archinetai/smart-pytorch · +3 2019
3 T5-3B 97.4–– Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer huggingface/transformers · PaddlePaddle/PaddleNLP · google-research/text-to-text-transfer-transformer · +54 2019
3 MUPPET Roberta Large 97.4–– Muppet: Massive Multi-task Representations with Pre-Finetuning facebook/muppet-roberta-base · facebook/muppet-roberta-large 2021
5 ALBERT 97.1–– ALBERT: A Lite BERT for Self-supervised Learning of Language Representations huggingface/transformers · tensorflow/models · PaddlePaddle/PaddleNLP · +45 2019
5 StructBERTRoBERTa ensemble 97.1–– StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding 2019
7 XLNet (single model) 97–– XLNet: Generalized Autoregressive Pretraining for Language Understanding huggingface/transformers · PaddlePaddle/PaddleNLP · zihangdai/xlnet · +24 2019
8 ELECTRA 96.9–– ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators huggingface/transformers · tensorflow/models · PaddlePaddle/PaddleNLP · +16 2020
8 RoBERTa-large 355M + Entailment as Few-shot Learner 96.9–– Entailment as Few-Shot Learner PaddlePaddle/PaddleNLP · sunyilgdx/prompts4keras · cactilab/hateguard 2021
10 XLNet-Large (ensemble) 96.8–– XLNet: Generalized Autoregressive Pretraining for Language Understanding huggingface/transformers · PaddlePaddle/PaddleNLP · zihangdai/xlnet · +24 2019
11 FLOATER-large 96.7–– Learning to Encode Position for Transformer with Continuous Dynamical Model xuanqing94/FLOATER 2020
11 MUPPET Roberta base 96.7–– Muppet: Massive Multi-task Representations with Pre-Finetuning facebook/muppet-roberta-base · facebook/muppet-roberta-large 2021
11 RoBERTa (ensemble) 96.7–– RoBERTa: A Robustly Optimized BERT Pretraining Approach huggingface/transformers · pytorch/fairseq · PaddlePaddle/PaddleNLP · +64 2019
14 DeBERTa (large) 96.5–– DeBERTa: Decoding-enhanced BERT with Disentangled Attention huggingface/transformers · microsoft/DeBERTa · osu-nlp-group/mind2web · +11 2020
14 MT-DNN-ensemble 96.5–– Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding namisan/mt-dnn · microsoft/MT-DNN · chunhuililili/mt_dnn 2019
16 RoBERTa-large 355M (MLP quantized vector-wise, fine-tuned) 96.4–– LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale timdettmers/bitsandbytes · huggingface/transformers-bloom-inference · kohjingyu/fromage · +1 2022
17 ASA + RoBERTa 96.3–– Adversarial Self-Attention for Language Understanding gingasan/adversarialsa 2022
17 T5-Large 770M 96.3–– Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer huggingface/transformers · PaddlePaddle/PaddleNLP · google-research/text-to-text-transfer-transformer · +54 2019
19 Snorkel MeTaL(ensemble) 96.2–– Training Complex Models with Multi-Task Weak Supervision HazyResearch/metal 2018
19 PSQ (Chen et al., 2020) 96.2–– A Statistical Framework for Low-bitwidth Training of Deep Neural Networks cjf00000/StatQuant · gaochang-bjtu/1-bit-fqt 2020
1–20 / 87 다음 → 페이지당 10 20 50 100