{"url":"/dataset/kptimes","name":"KPTimes","full_name":null,"description_markdown":"KPTimes is a large-scale dataset of news texts paired with editor-curated keyphrases. \r\n\r\nSource: [KPTimes: A Large-Scale Dataset for Keyphrase Generation on News Documents](/paper/kptimes-a-large-scale-dataset-for-keyphrase-1)","description_withheld":null,"homepage":"https://github.com/ygorg/KPTimes","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/kptimes-a-large-scale-dataset-for-keyphrase-1","title":"KPTimes: A Large-Scale Dataset for Keyphrase Generation on News Documents","first_author":"Ygor Gallina","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Keyphrase Extraction","url":"/task/keyphrase-extraction","datasets_with_task":"/datasets/task/keyphrase-extraction"},{"name":"Keyword Extraction","url":"/task/keyword-extraction","datasets_with_task":"/datasets/task/keyword-extraction"},{"name":"Phrase Ranking","url":"/task/phrase-ranking","datasets_with_task":"/datasets/task/phrase-ranking"},{"name":"Phrase Tagging","url":"/task/phrase-tagging","datasets_with_task":"/datasets/task/phrase-tagging"}],"languages":[],"variants":["KPTimes"],"data_loaders":[{"repo":"https://github.com/ygorg/KPTimes","url":"https://github.com/ygorg/KPTimes","frameworks":[]}],"num_papers_in_archive":27,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/keyphrase-extraction-on-kptimes","task":"Keyphrase Extraction","dataset_variant":"KPTimes","rows":4,"metrics":["Recall","F1@10"],"first_row_in_archive_order":{"model":"UCPhrase","paper":"/paper/ucphrase-unsupervised-context-aware-quality","metrics":{"F1@10":"10.9","Recall":"83.4"},"code_links":[{"title":"xgeric/UCPhrase-reproduce","url":"https://github.com/xgeric/UCPhrase-reproduce"},{"title":"xgeric/UCPhrase-exp","url":"https://github.com/xgeric/UCPhrase-exp"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/phrase-ranking-on-kptimes","task":"Phrase Ranking","dataset_variant":"KPTimes","rows":4,"metrics":["P@5K","P@50K"],"first_row_in_archive_order":{"model":"Wiki+RoBERTa","paper":"/paper/ucphrase-unsupervised-context-aware-quality","metrics":{"P@50K":" 96.5","P@5K":"99.0"},"code_links":[{"title":"xgeric/UCPhrase-reproduce","url":"https://github.com/xgeric/UCPhrase-reproduce"},{"title":"xgeric/UCPhrase-exp","url":"https://github.com/xgeric/UCPhrase-exp"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/phrase-tagging-on-kptimes","task":"Phrase Tagging","dataset_variant":"KPTimes","rows":4,"metrics":["Precision","Recall","F1"],"first_row_in_archive_order":{"model":"UCPhrase","paper":"/paper/ucphrase-unsupervised-context-aware-quality","metrics":{"F1":"73.5","Precision":"69.1","Recall":"78.9"},"code_links":[{"title":"xgeric/UCPhrase-reproduce","url":"https://github.com/xgeric/UCPhrase-reproduce"},{"title":"xgeric/UCPhrase-exp","url":"https://github.com/xgeric/UCPhrase-exp"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/ucphrase-unsupervised-context-aware-quality","title":"UCPhrase: Unsupervised Context-aware Quality Phrase Tagging","date":"2021-05-28","rows_on_this_dataset":12,"code_links":2,"syntology":null}],"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."}