{"url":"/dataset/oasum","name":"OASum","full_name":null,"description_markdown":"**OASum** is a large-scale open-domain aspect-based summarization dataset which contains more than 3.7 million instances with around 1 million different aspects on 2 million Wikipedia pages.\r\n\r\nSource: [OASum: Large-Scale Open Domain Aspect-based Summarization](https://arxiv.org/pdf/2212.09233v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2212.09233v1.pdf](https://arxiv.org/pdf/2212.09233v1.pdf)","description_withheld":null,"homepage":"https://github.com/tencent-ailab/OASum","introduced_date":"2022-12-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/oasum-large-scale-open-domain-aspect-based","title":"OASum: Large-Scale Open Domain Aspect-based Summarization","first_author":"Xianjun Yang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["OASum"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}