{"url":"/dataset/20newsgroup-10-tasks","name":"20Newsgroup (10 tasks)","full_name":null,"description_markdown":"This dataset has 20 classes and each class has about 1000 documents. The data split for train/validation/test is 1600/200/200. We created 10 tasks, 2\r\nclasses per task.  Since this is topic-based text classification data, the classes are very different and have little shared knowledge. As mentioned above, this application (and dataset) is mainly used to show a CL model's ability to overcome forgetting. Detailed statistics please on page https://github.com/ZixuanKe/PyContinual","description_withheld":null,"homepage":"https://github.com/ZixuanKe/PyContinual","introduced_date":"2021-12-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/achieving-forgetting-prevention-and-knowledge-1","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","first_author":"Zixuan Ke","url":null},"license":null,"modalities":[],"tasks":[{"name":"Continual Learning","url":"/task/continual-learning","datasets_with_task":"/datasets/task/continual-learning"},{"name":"Topic Classification","url":"/task/topic-classification","datasets_with_task":"/datasets/task/topic-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["20Newsgroup (10 tasks)"],"data_loaders":[],"num_papers_in_archive":11,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/continual-learning-on-20newsgroup-10-tasks","task":"Continual Learning","dataset_variant":"20Newsgroup (10 tasks)","rows":6,"metrics":["F1 - macro"],"first_row_in_archive_order":{"model":"CTR","paper":"/paper/achieving-forgetting-prevention-and-knowledge-1","metrics":{"F1 - macro":"0.9523"},"code_links":[{"title":"zixuanke/pycontinual","url":"https://github.com/zixuanke/pycontinual"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/continual-learning-of-a-mixed-sequence-of-1","title":"Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks","date":"2021-12-18","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/adapting-bert-for-continual-learning-of-a-1","title":"Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks","date":"2021-12-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/achieving-forgetting-prevention-and-knowledge-1","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","date":"2021-12-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/lamal-language-modeling-is-all-you-need-for","title":"LAMOL: LAnguage MOdeling for Lifelong Language Learning","date":"2019-09-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":1,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/overcoming-catastrophic-forgetting-with-hard","title":"Overcoming catastrophic forgetting with hard attention to the task","date":"2018-01-04","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/overcoming-catastrophic-forgetting-in-neural","title":"Overcoming catastrophic forgetting in neural networks","date":"2016-12-02","rows_on_this_dataset":1,"code_links":29,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":22,"samples_ran":14,"samples_unverified":8,"pointer_only_for_licence":4,"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":2,"samples_harvested":32,"samples_ran":15,"samples_unverified":17,"pointer_only_for_licence":4,"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."}