{"url":"/dataset/imdb-movie-reviews","name":"IMDb Movie Reviews","full_name":null,"description_markdown":"The **IMDb Movie Reviews** dataset is a binary sentiment analysis dataset consisting of 50,000 reviews from the Internet Movie Database (IMDb) labeled as positive or negative. The dataset contains an even number of positive and negative reviews. Only highly polarizing reviews are considered. A negative review has a score ≤ 4 out of 10, and a positive review has a score ≥ 7 out of 10. No more than 30 reviews are included per movie. The dataset contains additional unlabeled data.\r\n\r\nSource: [http://nlpprogress.com/english/sentiment_analysis.html](http://nlpprogress.com/english/sentiment_analysis.html)\r\nImage Source: [Maas et al](https://www.aclweb.org/anthology/P11-1015/)","description_withheld":null,"homepage":"https://ai.stanford.edu/~amaas/data/sentiment/","introduced_date":"2011-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Learning Word Vectors for Sentiment Analysis","first_author":null,"url":"https://www.aclweb.org/anthology/P11-1015/"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"},{"name":"Link Prediction","url":"/task/link-prediction","datasets_with_task":"/datasets/task/link-prediction"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Node Clustering","url":"/task/node-clustering","datasets_with_task":"/datasets/task/node-clustering"},{"name":"Paraphrase Identification","url":"/task/paraphrase-identification","datasets_with_task":"/datasets/task/paraphrase-identification"},{"name":"SQL Parsing","url":"/task/sql-parsing","datasets_with_task":"/datasets/task/sql-parsing"},{"name":"Opinion Mining","url":"/task/opinion-mining","datasets_with_task":"/datasets/task/opinion-mining"},{"name":"Graph Similarity","url":"/task/graph-similarity","datasets_with_task":"/datasets/task/graph-similarity"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["IMDb","IMDb Movie Reviews","User and product information"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jsburner/6be9adb1-3efe-4f31-97ad-1b30c79d20d2-imdb","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/saba9/1745497107-imdb","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/saba9/1745534874-imdb","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/imdb","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/lewtun/autoevaluate__imdb","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/yhavinga/imdb_dutch","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/josianem/imdb","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/pietrolesci/imdb_indexed","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/pietrolesci/imdb","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/davanstrien/test_imdb_embedd2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/davanstrien/test1","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/davanstrien/test_imdb_embedd","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/pietrolesci/_imdb","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/pt-sk/imdb","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/stanfordnlp/imdb","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/raulgdp/mendelay-HU","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Kwaai/IMDB_Sentiment","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Ahmedmasry/AES","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jsulz/1731088798-imdbrandom","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/imdb_reviews","frameworks":["tf","jax"]},{"repo":"https://github.com/pytorch/text","url":"https://pytorch.org/text/stable/datasets.html#torchtext.datasets.IMDB","frameworks":["pytorch"]}],"num_papers_in_archive":1787,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset_variant":"IMDb","rows":49,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"RoBERTa-large with LlamBERT","paper":"/paper/llambert-large-scale-low-cost-data-annotation","metrics":{"Accuracy":"96.68"},"code_links":[{"title":"aielte-research/llambert","url":"https://github.com/aielte-research/llambert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/opinion-mining-on-imdb-movie-reviews","task":"Opinion Mining","dataset_variant":"IMDb Movie Reviews","rows":15,"metrics":["Accuracy","F1"],"first_row_in_archive_order":{"model":"ELECTRA","paper":"/paper/analysis-of-the-evolution-of-advanced","metrics":{"Accuracy":"95.6","F1":"95.6"},"code_links":[{"title":"zekaouinoureddine/Opinion-Transformers","url":"https://github.com/zekaouinoureddine/Opinion-Transformers"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-classification-on-imdb","task":"Text Classification","dataset_variant":"IMDb","rows":13,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":{"model":"BERT-ITPT-FiT","paper":"/paper/how-to-fine-tune-bert-for-text-classification","metrics":{},"code_links":[{"title":"xuyige/BERT4doc-Classification","url":"https://github.com/xuyige/BERT4doc-Classification"},{"title":"ongunuzaymacar/comparatively-finetuning-bert","url":"https://github.com/ongunuzaymacar/comparatively-finetuning-bert"},{"title":"uzaymacar/comparatively-finetuning-bert","url":"https://github.com/uzaymacar/comparatively-finetuning-bert"},{"title":"helmy-elrais/RoBERT_Recurrence_over_BERT","url":"https://github.com/helmy-elrais/RoBERT_Recurrence_over_BERT"},{"title":"GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data","url":"https://github.com/GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data"},{"title":"heraclex12/VLSP2020-Fake-News-Detection","url":"https://github.com/heraclex12/VLSP2020-Fake-News-Detection"},{"title":"bcaitech1/p4-dkt-no_caffeine_no_gain","url":"https://github.com/bcaitech1/p4-dkt-no_caffeine_no_gain"},{"title":"soarsmu/BiasFinder","url":"https://github.com/soarsmu/BiasFinder"},{"title":"qinhanmin2014/fine-tune-bert-for-text-classification","url":"https://github.com/qinhanmin2014/fine-tune-bert-for-text-classification"},{"title":"Domminique/Deploy-BERT-for-Sentiment-Analysis-with-FastAPI-","url":"https://github.com/Domminique/Deploy-BERT-for-Sentiment-Analysis-with-FastAPI-"},{"title":"Derposoft/ai-educator","url":"https://github.com/Derposoft/ai-educator"},{"title":"arctic-yen/Google_QUEST_Q-A_Labeling","url":"https://github.com/arctic-yen/Google_QUEST_Q-A_Labeling"},{"title":"sahil00199/KYC","url":"https://github.com/sahil00199/KYC"},{"title":"jyp1111/sentiment_analysis","url":"https://github.com/jyp1111/sentiment_analysis"},{"title":"saproovarun/Google-Quest-Q-A","url":"https://github.com/saproovarun/Google-Quest-Q-A"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/sentiment-analysis-on-user-and-product","task":"Sentiment Analysis","dataset_variant":"User and product information","rows":10,"metrics":["IMDB (Acc)","Yelp 2013 (Acc)","Yelp 2014 (Acc)"],"first_row_in_archive_order":{"model":"MA-BERT","paper":"/paper/ma-bert-learning-representation-by","metrics":{"IMDB (Acc)":"57.3","Yelp 2013 (Acc)":"70.3","Yelp 2014 (Acc)":"71.4"},"code_links":[{"title":"yoyo-yun/ma-bert","url":"https://github.com/yoyo-yun/ma-bert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-classification-on-imdb-movie-reviews-1","task":"Text Classification","dataset_variant":"IMDb Movie Reviews","rows":3,"metrics":["AUC","Accuracy (2 classes)","F1 Macro"],"first_row_in_archive_order":{"model":"Logistic Regression","paper":"/paper/anytime-active-learning","metrics":{"AUC":"0.84"},"code_links":[{"title":"Bhavneet1492/Anytime-Active-Learning","url":"https://github.com/Bhavneet1492/Anytime-Active-Learning"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/sentiment-analysis-on-imdb-movie-reviews-1","task":"Sentiment Analysis","dataset_variant":"IMDb Movie Reviews","rows":2,"metrics":["Accuracy (2 classes)","F1 Macro"],"first_row_in_archive_order":{"model":"Space-XLNet","paper":"/paper/breaking-free-transformer-models-task","metrics":{"Accuracy (2 classes)":"0.9488","F1 Macro":"0.9487"},"code_links":[{"title":"stepantita/space-model","url":"https://github.com/stepantita/space-model"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/graph-similarity-on-imdb","task":"Graph Similarity","dataset_variant":"IMDb","rows":1,"metrics":["mse (10^-3)"],"first_row_in_archive_order":{"model":"SimGNN","paper":"/paper/graph-edit-distance-computation-via-graph","metrics":{"mse (10^-3)":"1.264"},"code_links":[{"title":"benedekrozemberczki/SimGNN","url":"https://github.com/benedekrozemberczki/SimGNN"},{"title":"pulkit1joshi/SimGNN","url":"https://github.com/pulkit1joshi/SimGNN"},{"title":"Sangs3112/SimGNN","url":"https://github.com/Sangs3112/SimGNN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/link-prediction-on-imdb","task":"Link Prediction","dataset_variant":"IMDb","rows":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"Event2vec","paper":"/paper/representation-learning-for-heterogeneous","metrics":{"AUC":"89.4"},"code_links":[{"title":"fuguoji/Event2vec","url":"https://github.com/fuguoji/Event2vec"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/paraphrase-identification-on-imdb","task":"Paraphrase Identification","dataset_variant":"IMDb","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SplitEE-S","paper":"/paper/splitee-early-exit-in-deep-neural-networks","metrics":{"Accuracy":"82.2"},"code_links":[{"title":"Div290/SplitEE","url":"https://github.com/Div290/SplitEE/blob/main/README.md"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/learning-in-wilson-cowan-model-for","title":"Learning in Wilson-Cowan model for metapopulation","date":"2024-06-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/llambert-large-scale-low-cost-data-annotation","title":"LlamBERT: Large-scale low-cost data annotation in NLP","date":"2024-03-23","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/breaking-free-transformer-models-task","title":"Breaking Free Transformer Models: Task-specific Context Attribution Promises Improved Generalizability Without Fine-tuning Pre-trained LLMs","date":"2024-01-30","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/cache-me-if-you-can-an-online-cost-aware","title":"Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language Models","date":"2023-10-20","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/splitee-early-exit-in-deep-neural-networks","title":"SplitEE: Early Exit in Deep Neural Networks with Split Computing","date":"2023-09-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/analysis-of-the-evolution-of-advanced","title":"Analysis of the Evolution of Advanced Transformer-Based Language Models: Experiments on Opinion Mining","date":"2023-08-07","rows_on_this_dataset":15,"code_links":1,"syntology":null},{"paper":"/paper/an-algorithm-for-routing-vectors-in-sequences","title":"An Algorithm for Routing Vectors in Sequences","date":"2022-11-20","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/the-document-vectors-using-cosine-similarity-1","title":"The Document Vectors Using Cosine Similarity Revisited","date":"2022-05-26","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/context-aware-compilation-of-dnn-training","title":"Context-Aware Compilation of DNN Training Pipelines across Edge and Cloud","date":"2021-12-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","rows_on_this_dataset":2,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ma-bert-learning-representation-by","title":"MA-BERT: Learning Representation by Incorporating Multi-Attribute Knowledge in Transformers","date":"2021-08-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/closed-form-continuous-depth-models","title":"Closed-form Continuous-time Neural Models","date":"2021-06-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":2,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/classifying-textual-data-with-pre-trained","title":"Classifying Textual Data with Pre-trained Vision Models through Transfer Learning and Data Transformations","date":"2021-06-23","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","date":"2021-04-29","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unicornn-a-recurrent-model-for-learning-very","title":"UnICORNN: A recurrent model for learning very long time dependencies","date":"2021-03-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improving-document-level-sentiment","title":"Improving Document-Level Sentiment Classification Using Importance of Sentences","date":"2021-03-09","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/parallelizing-legendre-memory-unit-training","title":"Parallelizing Legendre Memory Unit Training","date":"2021-02-22","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/nystromformer-a-nystrom-based-algorithm-for","title":"Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention","date":"2021-02-07","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ernie-doc-the-retrospective-long-document","title":"ERNIE-Doc: A Retrospective Long-Document Modeling Transformer","date":"2020-12-31","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/neural-semi-supervised-learning-for-text","title":"Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining","date":"2020-11-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-pre-trained-language-model-with","title":"Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach","date":"2020-10-15","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/coupled-oscillatory-recurrent-neural-network","title":"Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies","date":"2020-10-02","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/revisiting-lstm-networks-for-semi-supervised-1","title":"Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function","date":"2020-09-08","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bp-transformer-modelling-long-range-context","title":"BP-Transformer: Modelling Long-Range Context via Binary Partitioning","date":"2019-11-11","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","rows_on_this_dataset":1,"code_links":37,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":27,"samples_ran":19,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-attribute-representation-and","title":"Rethinking Attribute Representation and Injection for Sentiment Classification","date":"2019-08-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/message-passing-attention-networks-for","title":"Message Passing Attention Networks for Document Understanding","date":"2019-08-17","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/sentiment-classification-using-document","title":"Sentiment Classification Using Document Embeddings Trained with Cosine Similarity","date":"2019-07-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/graph-star-net-for-generalized-multi-task-1","title":"Graph Star Net for Generalized Multi-Task Learning","date":"2019-06-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":24,"samples_ran":10,"samples_unverified":14,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/how-to-fine-tune-bert-for-text-classification","title":"How to Fine-Tune BERT for Text Classification?","date":"2019-05-14","rows_on_this_dataset":3,"code_links":15,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":6,"samples_unverified":12,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unsupervised-data-augmentation-1","title":"Unsupervised Data Augmentation for Consistency Training","date":"2019-04-29","rows_on_this_dataset":2,"code_links":20,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":52,"samples_ran":15,"samples_unverified":37,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/docbert-bert-for-document-classification","title":"DocBERT: BERT for Document Classification","date":"2019-04-17","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":0,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","rows_on_this_dataset":1,"code_links":21,"syntology":null},{"paper":"/paper/categorical-metadata-representation-for","title":"Categorical Metadata Representation for Customized Text Classification","date":"2019-02-14","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/representation-learning-for-heterogeneous","title":"Representation Learning for Heterogeneous Information Networks via Embedding Events","date":"2019-01-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-attentional-hybrid-neural","title":"Hierarchical Attentional Hybrid Neural Networks for Document Classification","date":"2019-01-20","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/long-short-term-memory-with-dynamic-skip","title":"Long Short-Term Memory with Dynamic Skip Connections","date":"2018-11-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dual-memory-network-model-for-biased-product","title":"Dual Memory Network Model for Biased Product Review Classification","date":"2018-09-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/graph-edit-distance-computation-via-graph","title":"SimGNN: A Neural Network Approach to Fast Graph Similarity Computation","date":"2018-08-16","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/task-oriented-word-embedding-for-text","title":"Task-oriented Word Embedding for Text Classification","date":"2018-08-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cold-start-aware-user-and-product-attention","title":"Cold-Start Aware User and Product Attention for Sentiment Classification","date":"2018-06-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/information-aggregation-via-dynamic-routing","title":"Information Aggregation via Dynamic Routing for Sequence Encoding","date":"2018-06-05","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/a-la-carte-embedding-cheap-but-effective","title":"A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors","date":"2018-05-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sentence-state-lstm-for-text-representation","title":"Sentence-State LSTM for Text Representation","date":"2018-05-07","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improving-review-representations-with-user","title":"Improving Review Representations with User Attention and Product Attention for Sentiment Classification","date":"2018-01-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/universal-language-model-fine-tuning-for-text","title":"Universal Language Model Fine-tuning for Text Classification","date":"2018-01-18","rows_on_this_dataset":1,"code_links":66,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/gpu-kernels-for-block-sparse-weights","title":"GPU Kernels for Block-Sparse Weights","date":"2017-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cascading-multiway-attentions-for-document","title":"Cascading Multiway Attentions for Document-level Sentiment Classification","date":"2017-11-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/capturing-user-and-product-information-for","title":"Capturing User and Product Information for Document Level Sentiment Analysis with Deep Memory Network","date":"2017-09-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learned-in-translation-contextualized-word","title":"Learned in Translation: Contextualized Word Vectors","date":"2017-08-01","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficient-vector-representation-for-documents","title":"Efficient Vector Representation for Documents through Corruption","date":"2017-07-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/on-the-role-of-text-preprocessing-in-neural","title":"On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis","date":"2017-07-06","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/contextual-explanation-networks","title":"Contextual Explanation Networks","date":"2017-05-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/neural-sentiment-classification-with-user-and","title":"Neural Sentiment Classification with User and Product Attention","date":"2016-11-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adversarial-training-methods-for-semi","title":"Adversarial Training Methods for Semi-Supervised Text Classification","date":"2016-05-25","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/supervised-and-semi-supervised-text","title":"Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings","date":"2016-02-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-semantic-representations-of-users","title":"Learning Semantic Representations of Users and Products for Document Level Sentiment Classification","date":"2015-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-convolutional-neural-networks-1","title":"Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding","date":"2015-04-06","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/effective-use-of-word-order-for-text-1","title":"Effective Use of Word Order for Text Categorization with Convolutional Neural Networks","date":"2014-12-01","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/anytime-active-learning","title":"Anytime Active Learning","date":"2014-07-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/distributed-representations-of-sentences-and","title":"Distributed Representations of Sentences and Documents","date":"2014-05-16","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":22,"samples_harvested":194,"samples_ran":68,"samples_unverified":126,"pointer_only_for_licence":28,"papers_with_no_sample_that_ran":6,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}