{"url":"/dataset/k-sportssum","name":"K-SportsSum","full_name":null,"description_markdown":"K-SportsSum is a sports game summarization dataset with two characteristics: (1) K-SportsSum collects a large amount of data from massive games. It has 7,854 commentary-news pairs. To improve the quality, K-SportsSum employs a manual cleaning process; (2) Different from existing datasets, to narrow the knowledge gap, K-SportsSum further provides a large-scale knowledge corpus that contains the information of 523 sports teams and 14,724 sports players.","description_withheld":null,"homepage":"https://github.com/krystalan/K-SportsSum","introduced_date":"2021-11-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/knowledge-enhanced-sports-game-summarization","title":"Knowledge Enhanced Sports Game Summarization","first_author":"Jiaan Wang","url":null},"license":{"name":"CC BY-NC-SA 4.0","url":"https://creativecommons.org/licenses/by-nc-sa/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Mandarin Chinese","url":"/datasets/language/mandarin-chinese"}],"variants":["K-SportsSum"],"data_loaders":[],"num_papers_in_archive":2,"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."}