paper-with-me

Sentiment Analysis 벤치마크

Sentiment Analysis on IMDb

52개 결과 · ⬇ CSV · JSON

Accuracy

30.3 46.99 63.69 80.38 97.07 2014-12 2026-09 seq2-bown-CNN — 92.33 (2014-12-01) oh-LSTM — 94.1 (2016-02-07) Virtual adversarial training — 94.1 (2016-05-25) CEN-tpc — 94.52 (2017-05-29) CNN+LSTM — 88.9 (2017-07-06) Doc2VecC — 88.3 (2017-07-08) BCN+Char+CoVe — 91.8 (2017-08-01) Block-sparse LSTM — 94.99 (2017-12-01) ULMFiT — 95.4 (2018-01-18) S-LSTM — 87.15 (2018-05-07) Standard DR-AGG — 45.1 (2018-06-05) Reverse DR-AGG — 44.5 (2018-06-05) ToWE-SG — 90.8 (2018-08-01) LSTM with dynamic skip — 90.1 (2018-11-09) GPT-2 Finetuned — 92.36 (2019-02-14) BERT large finetune UDA — 95.8 (2019-04-29) BERT large — 95.49 (2019-04-29) BERT_large+ITPT — 95.79 (2019-05-14) BERT_base+ITPT — 95.63 (2019-05-14) XLNet — 96.21 (2019-06-19) GraphStar — 96.0 (2019-06-21) DV-ngrams-cosine — 93.13 (2019-07-01) DistilBERT 66M — 92.82 (2019-10-02) BP-Transformer + GloVe — 92.12 (2019-11-11) L MIXED — 95.68 (2020-09-08) coRNN — 87.4 (2020-10-02) COSINE — 90.54 (2020-10-15) Nyströmformer — 93.2 (2021-02-07) Modified LMU (34M) — 93.2 (2021-02-22) UnICORNN — 88.4 (2021-03-09) RoBERTa-large 355M + Entailment as Few-shot Learner — 96.1 (2021-04-29) AlexNet [alexnet] — 87.0 (2021-06-23) VGG16 [vgg16] — 86.0 (2021-06-23) ResNext[resnext] — 85.0 (2021-06-23) CfC — 88.4 (2021-06-25) FLAN 137B (few-shot, k=2) — 95.0 (2021-09-03) FLAN 137B (zero-shot) — 94.3 (2021-09-03) DV-ngrams-cosine with NB sub-sampling + RoBERTa.base — 95.94 (2022-05-26) DV-ngrams-cosine + RoBERTa.base — 95.92 (2022-05-26) RoBERTa.base — 95.79 (2022-05-26) DV-ngrams-cosine + NB-weighted BON (re-evaluated) — 93.68 (2022-05-26) Heinsen Routing + RoBERTa Large — 96.2 (2022-11-20) OCaTS (kNN & GPT-3.5-turbo — 93.06 (2023-10-20) Space-XLNet — 94.88 (2024-01-30) RoBERTa-large with LlamBERT — 96.68 (2024-03-23) RoBERTa-large — 96.54 (2024-03-23) Llama-2-70b-chat (0-shot) — 95.39 (2024-03-23) Bert+ Wilson-Cowan model RNN — 87.46 (2024-06-24) Enhancing Sentiment Classification with — 97.072 (2025-10-30) CISEA-MRFE — 30.3 (2025-11-01) Enhancing Hyperspace Analogue to Languag — 82.38 (2026-03-20) seq2-bown-CNN — 92.33 (2014-12-01) oh-LSTM — 94.1 (2016-02-07) CEN-tpc — 94.52 (2017-05-29) Block-sparse LSTM — 94.99 (2017-12-01) ULMFiT — 95.4 (2018-01-18) BERT large finetune UDA — 95.8 (2019-04-29) XLNet — 96.21 (2019-06-19) RoBERTa-large with LlamBERT — 96.68 (2024-03-23) Enhancing Sentiment Classification with — 97.072 (2025-10-30)
RankModel Accuracy Extra Training Data PaperCodeYear
21 Space-XLNet 94.88 Breaking Free Transformer Models: Task-specific Context Attribution Promises Improved Generalizability Without Fine-tuning Pre-trained LLMs stepantita/space-model 2024
22 CEN-tpc 94.52 Contextual Explanation Networks alshedivat/cen 2017
23 FLAN 137B (zero-shot) 94.3 ✓ Finetuned Language Models Are Zero-Shot Learners hiyouga/llama-efficient-tuning · bigcode-project/starcoder · bigscience-workshop/promptsource · +5 2021
24 oh-LSTM 94.1 ✓ Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings 2016
24 Virtual adversarial training 94.1 Adversarial Training Methods for Semi-Supervised Text Classification tensorflow/models · tensorflow/models · TobiasLee/Text-Classification · +1 2016
26 DV-ngrams-cosine + NB-weighted BON (re-evaluated) 93.68 The Document Vectors Using Cosine Similarity Revisited bgzh/dv_cosine_revisited 2022
27 Nyströmformer 93.2 Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention facebookresearch/xformers · mlpen/Nystromformer · lucidrains/nystrom-attention · +7 2021
27 Modified LMU (34M) 93.20 Parallelizing Legendre Memory Unit Training hrshtv/pytorch-lmu · elisejiuqizhang/jax-lmu 2021
29 DV-ngrams-cosine 93.13 Sentiment Classification Using Document Embeddings Trained with Cosine Similarity tanthongtan/dv-cosine · bgzh/dv_cosine_revisited 2019
30 OCaTS (kNN & GPT-3.5-turbo 93.06 Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language Models stoyian/OCaTS 2023
31 DistilBERT 66M 92.82 DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter huggingface/transformers · PaddlePaddle/PaddleNLP · huggingface/swift-coreml-transformers · +34 2019
32 GPT-2 Finetuned 92.36 Language Models are Unsupervised Multitask Learners huggingface/transformers · openai/gpt-2 · PaddlePaddle/PaddleNLP · +18 2019
33 seq2-bown-CNN 92.33 Effective Use of Word Order for Text Categorization with Convolutional Neural Networks tensorflow/models · tensorflow/models · jean-kunz/ml_research_papers · +1 2014
34 BP-Transformer + GloVe 92.12 BP-Transformer: Modelling Long-Range Context via Binary Partitioning dmlc/dgl · yzh119/BPT 2019
35 BCN+Char+CoVe 91.8 Learned in Translation: Contextualized Word Vectors salesforce/cove · adi2103/AML-CoVe · menajosep/AleatoricSent · +2 2017
36 ToWE-SG 90.8 Task-oriented Word Embedding for Text Classification qianliu0708/ToWE 2018
37 COSINE 90.54 Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach yueyu1030/COSINE 2020
38 LSTM with dynamic skip 90.1 Long Short-Term Memory with Dynamic Skip Connections lecholin/DynamicLSTM 2018
39 CNN+LSTM 88.9 ✓ On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis pedrada88/preproc-textclassification · changji2069/Scope-Project · changji2069/literature-review 2017
40 UnICORNN 88.4 UnICORNN: A recurrent model for learning very long time dependencies tk-rusch/unicornn 2021
← 이전 21–40 / 52 다음 → 페이지당 10 20 50 100