{"url":"/dataset/20-newsgroups","name":"20 Newsgroups","full_name":null,"description_markdown":"The 20 Newsgroups data set is a collection of approximately 20,000 newsgroup documents, partitioned (nearly) evenly across 20 different newsgroups.","description_withheld":null,"homepage":"http://qwone.com/~jason/20Newsgroups/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Out-of-Distribution Detection","url":"/task/out-of-distribution-detection","datasets_with_task":"/datasets/task/out-of-distribution-detection"},{"name":"Text Clustering","url":"/task/text-clustering","datasets_with_task":"/datasets/task/text-clustering"},{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"},{"name":"Topic Models","url":"/task/topic-models","datasets_with_task":"/datasets/task/topic-models"},{"name":"Supervised Text Retrieval","url":"/task/supervised-text-retrieval","datasets_with_task":"/datasets/task/supervised-text-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["20 Newsgroups"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/newsgroup","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/newsgroup","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/Graviti-AI/datasets","url":"https://gas.graviti.com/dataset/graviti/Newsgroups20","frameworks":["tf","pytorch"]}],"num_papers_in_archive":27,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-retrieval-on-20-newsgroups","task":"Text Retrieval","dataset_variant":"20 Newsgroups","rows":3,"metrics":["Precision@100"],"first_row_in_archive_order":{"model":"B-VAE","paper":"/paper/a-binary-variational-autoencoder-for-hashing","metrics":{"Precision@100":"0.441"},"code_links":[{"title":"fmenat/DiscreteVAE","url":"https://github.com/fmenat/DiscreteVAE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/out-of-distribution-detection-on-20","task":"Out-of-Distribution Detection","dataset_variant":"20 Newsgroups","rows":2,"metrics":["AUROC","FPR95"],"first_row_in_archive_order":{"model":"2-Layered GRU","paper":"/paper/an-effective-baseline-for-robustness-to","metrics":{"AUROC":"99.6","FPR95":"1.78"},"code_links":[{"title":"Sushil-Thapa/Abstention-OoD","url":"https://github.com/Sushil-Thapa/Abstention-OoD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-clustering-on-20-newsgroups","task":"Text Clustering","dataset_variant":"20 Newsgroups","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"G-BAT","paper":"/paper/neural-topic-modeling-with-bidirectional","metrics":{"Accuracy":"41.25"},"code_links":[{"title":"zll17/Neural_Topic_Models","url":"https://github.com/zll17/Neural_Topic_Models"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/topic-models-on-20-newsgroups","task":"Topic Models","dataset_variant":"20 Newsgroups","rows":2,"metrics":["Test perplexity"],"first_row_in_archive_order":{"model":"Bayesian SMM","paper":"/paper/190807599","metrics":{"Test perplexity":"515"},"code_links":[{"title":"skesiraju/BaySMM","url":"https://github.com/skesiraju/BaySMM"},{"title":"BUTSpeechFIT/BaySMM","url":"https://github.com/BUTSpeechFIT/BaySMM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-classification-on-20-newsgroups","task":"Text Classification","dataset_variant":"20 Newsgroups","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"RoBERTaGCN","paper":"/paper/bertgcn-transductive-text-classification-by","metrics":{"Accuracy":"89.5"},"code_links":[{"title":"ZeroRin/BertGCN","url":"https://github.com/ZeroRin/BertGCN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/an-effective-baseline-for-robustness-to","title":"An Effective Baseline for Robustness to Distributional Shift","date":"2021-05-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bertgcn-transductive-text-classification-by","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","date":"2021-05-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/neural-topic-modeling-with-bidirectional","title":"Neural Topic Modeling with Bidirectional Adversarial Training","date":"2020-04-26","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-binary-variational-autoencoder-for-hashing","title":"A Binary Variational Autoencoder for Hashing","date":"2019-10-22","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/190807599","title":"Learning document embeddings along with their uncertainties","date":"2019-08-20","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/simultaneous-classification-and-novelty","title":"Outlier Exposure with Confidence Control for Out-of-Distribution Detection","date":"2019-06-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/variational-deep-semantic-hashing-for-text","title":"Variational Deep Semantic Hashing for Text Documents","date":"2017-08-11","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/neural-variational-inference-for-text","title":"Neural Variational Inference for Text Processing","date":"2015-11-19","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":1,"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":1,"samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"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."}