{"url":"/dataset/kp20k","name":"KP20k","full_name":"KP20k","description_markdown":"**KP20k** is a large-scale scholarly articles dataset with 528K articles for training, 20K articles for validation and 20K articles for testing.\r\n\r\nSource: [Keyphrase Prediction With Pre-trained Language Model](https://arxiv.org/abs/2004.10462)\r\nImage Source: [https://arxiv.org/pdf/1704.06879.pdf](https://arxiv.org/pdf/1704.06879.pdf)","description_withheld":null,"homepage":"https://github.com/memray/seq2seq-keyphrase","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/deep-keyphrase-generation","title":"Deep Keyphrase Generation","first_author":"Rui Meng","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"},{"name":"Keyphrase Extraction","url":"/task/keyphrase-extraction","datasets_with_task":"/datasets/task/keyphrase-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":[{"name":"English","url":"/datasets/language/english"}],"variants":["KP20k"],"data_loaders":[{"repo":"https://github.com/memray/seq2seq-keyphrase","url":"https://github.com/memray/seq2seq-keyphrase","frameworks":["pytorch"]}],"num_papers_in_archive":87,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/keyphrase-extraction-on-kp20k","task":"Keyphrase Extraction","dataset_variant":"KP20k","rows":7,"metrics":["Recall","F1@10"],"first_row_in_archive_order":{"model":"Wiki+RoBERTa","paper":"/paper/ucphrase-unsupervised-context-aware-quality","metrics":{"F1@10":"19.2","Recall":"73.0"},"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-kp20k","task":"Phrase Tagging","dataset_variant":"KP20k","rows":4,"metrics":["Precision","Recall","F1"],"first_row_in_archive_order":{"model":"UCPhrase","paper":"/paper/ucphrase-unsupervised-context-aware-quality","metrics":{"F1":"73.9","Precision":"69.9","Recall":"78.3"},"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-kp20k","task":"Phrase Ranking","dataset_variant":"KP20k","rows":3,"metrics":["P@5K","P@50K"],"first_row_in_archive_order":{"model":"Wiki+RoBERTa","paper":"/paper/ucphrase-unsupervised-context-aware-quality","metrics":{"P@50K":"98.5","P@5K":"100.0"},"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"}],"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":14,"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."}