{"url":"/dataset/asc-til-19-tasks","name":"ASC (TIL, 19 tasks)","full_name":"Task Incremental Aspect Sentiment Classification","description_markdown":"A set of 19 ASC datasets (reviews of 19 products) producing a sequence of 19 tasks. Each dataset represents a task. The datasets are from 4 sources: (1) HL5Domains (Hu and Liu, 2004) with reviews of 5 products; (2) Liu3Domains (Liu et al., 2015) with reviews of 3 products; (3) Ding9Domains (Ding et al., 2008) with reviews of 9 products; and (4) SemEval14 with reviews of 2 products - SemEval 2014 Task 4 for laptop and restaurant. For (1), (2) and (3), we split about 10% of the original data as the validate data, another about 10% of the original data as the testing data. For (4), We use 150 examples from the training set for validation. To be consistent with existing research(Tang et al., 2016), examples belonging to the conflicting polarity (both positive and negative sentiments are expressed about an aspect term) are not used. Statistics and details of the 19 datasets are given on Page https://github.com/ZixuanKe/PyContinual.","description_withheld":null,"homepage":"https://github.com/ZixuanKe/PyContinual","introduced_date":"2021-12-06","introduced_date_note":null,"introduced_by":{"paper":"/paper/adapting-bert-for-continual-learning-of-a-1","title":"Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks","first_author":"Zixuan Ke","url":null},"license":null,"modalities":[],"tasks":[{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"},{"name":"Continual Learning","url":"/task/continual-learning","datasets_with_task":"/datasets/task/continual-learning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ASC (19 tasks)","ASC (TIL, 19 tasks)"],"data_loaders":[{"repo":"https://github.com/zixuanke/pycontinual","url":"https://github.com/zixuanke/pycontinual","frameworks":["pytorch"]}],"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-asc-19-tasks","task":"Continual Learning","dataset_variant":"ASC (19 tasks)","rows":15,"metrics":["F1 - macro"],"first_row_in_archive_order":{"model":"Multi-task Learning (MTL; Upper Bound)","paper":"/paper/achieving-forgetting-prevention-and-knowledge-1","metrics":{"F1 - macro":"0.8811"},"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-with-knowledge-transfer","title":"Continual Learning with Knowledge Transfer for Sentiment Classification","date":"2021-12-18","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"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":4,"code_links":1,"syntology":null},{"paper":"/paper/dark-experience-for-general-continual","title":"Dark Experience for General Continual Learning: a Strong, Simple Baseline","date":"2020-04-15","rows_on_this_dataset":1,"code_links":3,"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/uncertainty-based-continual-learning-with","title":"Uncertainty-based Continual Learning with Adaptive Regularization","date":"2019-05-28","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":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficient-lifelong-learning-with-a-gem","title":"Efficient Lifelong Learning with A-GEM","date":"2018-12-02","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":1,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/continuous-learning-of-context-dependent","title":"Continual Learning of Context-dependent Processing in Neural Networks","date":"2018-09-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":2,"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":4,"samples_harvested":45,"samples_ran":17,"samples_unverified":28,"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."}