{"url":"/task/keyphrase-extraction","name":"Keyphrase Extraction","slug":"keyphrase-extraction","description_markdown":"A classic task to extract salient phrases that best summarize a document, which essentially has two stages: candidate generation and keyphrase ranking.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":153,"papers_with_code":52,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":8,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/keyphrase-extraction-on-kp20k","slug":"keyphrase-extraction-on-kp20k","dataset":"KP20k","dataset_url":"/dataset/kp20k","rows_in_archive":7,"metrics":["Recall","F1@10"],"first_row_in_archive_order":{"model":"Wiki+RoBERTa","paper_title":"UCPhrase: Unsupervised Context-aware Quality Phrase Tagging","paper_url":"/paper/ucphrase-unsupervised-context-aware-quality","paper_date":"2021-05-28","arxiv_id":"2105.14078","code_links":[{"title":"xgeric/UCPhrase-reproduce","url":"https://github.com/xgeric/UCPhrase-reproduce"},{"title":"xgeric/UCPhrase-exp","url":"https://github.com/xgeric/UCPhrase-exp"}],"syntology":null}},{"leaderboard":"/sota/keyphrase-extraction-on-kptimes","slug":"keyphrase-extraction-on-kptimes","dataset":"KPTimes","dataset_url":"/dataset/kptimes","rows_in_archive":4,"metrics":["Recall","F1@10"],"first_row_in_archive_order":{"model":"UCPhrase","paper_title":"UCPhrase: Unsupervised Context-aware Quality Phrase Tagging","paper_url":"/paper/ucphrase-unsupervised-context-aware-quality","paper_date":"2021-05-28","arxiv_id":"2105.14078","code_links":[{"title":"xgeric/UCPhrase-reproduce","url":"https://github.com/xgeric/UCPhrase-reproduce"},{"title":"xgeric/UCPhrase-exp","url":"https://github.com/xgeric/UCPhrase-exp"}],"syntology":null}},{"leaderboard":"/sota/keyphrase-extraction-on-inspec","slug":"keyphrase-extraction-on-inspec","dataset":"Inspec","dataset_url":"/dataset/inspec","rows_in_archive":3,"metrics":["F1@10"],"first_row_in_archive_order":{"model":"Attention-Seeker","paper_title":"Attention-Seeker: Dynamic Self-Attention Scoring for Unsupervised Keyphrase Extraction","paper_url":"/paper/attention-seeker-dynamic-self-attention","paper_date":"2024-09-17","arxiv_id":"2409.10907","code_links":[{"title":"EruM16/Attention-Seeker","url":"https://github.com/EruM16/Attention-Seeker"}],"syntology":null}},{"leaderboard":"/sota/keyphrase-extraction-on-krapivin","slug":"keyphrase-extraction-on-krapivin","dataset":"Krapivin","dataset_url":"/dataset/krapivin","rows_in_archive":2,"metrics":["F1@10"],"first_row_in_archive_order":{"model":"Attention-Seeker","paper_title":"Attention-Seeker: Dynamic Self-Attention Scoring for Unsupervised Keyphrase Extraction","paper_url":"/paper/attention-seeker-dynamic-self-attention","paper_date":"2024-09-17","arxiv_id":"2409.10907","code_links":[{"title":"EruM16/Attention-Seeker","url":"https://github.com/EruM16/Attention-Seeker"}],"syntology":null}},{"leaderboard":"/sota/keyphrase-extraction-on-nus","slug":"keyphrase-extraction-on-nus","dataset":"NUS","dataset_url":"/dataset/nus","rows_in_archive":1,"metrics":["F1@10"],"first_row_in_archive_order":{"model":"PromptRank","paper_title":"PromptRank: Unsupervised Keyphrase Extraction Using Prompt","paper_url":"/paper/promptrank-unsupervised-keyphrase-extraction","paper_date":"2023-05-08","arxiv_id":"2305.04490","code_links":[{"title":"nku-hlt/promptrank","url":"https://github.com/nku-hlt/promptrank"},{"title":"hlt-nlp/promptrank","url":"https://github.com/hlt-nlp/promptrank"}],"syntology":null}}],"datasets":[{"url":"/dataset/kp20k","name":"KP20k","full_name":"KP20k","num_papers_in_archive":87},{"url":"/dataset/semeval2017","name":"SemEval-2017 Task-10","full_name":"","num_papers_in_archive":33},{"url":"/dataset/kptimes","name":"KPTimes","full_name":"","num_papers_in_archive":27},{"url":"/dataset/inspec","name":"Inspec","full_name":"","num_papers_in_archive":7},{"url":"/dataset/krapivin","name":"Krapivin","full_name":"","num_papers_in_archive":2},{"url":"/dataset/nus","name":"NUS","full_name":"","num_papers_in_archive":2},{"url":"/dataset/europa","name":"EUROPA","full_name":"","num_papers_in_archive":1},{"url":"/dataset/keyphrases-cs-math-russian","name":"Keyphrases CS&Math Russian","full_name":"Keyphrases CS&Math Russian","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":52,"tagged_in_all":153,"items":[{"url":"/paper/deep-keyphrase-generation","title":"Deep Keyphrase Generation","date":"2017-04-23","arxiv_id":"1704.06879","repositories_listed":4,"syntology":null},{"url":"/paper/enhancing-in-context-learning-with-answer","title":"Enhancing In-Context Learning with Answer Feedback for Multi-Span Question Answering","date":"2023-06-07","arxiv_id":"2306.04508","repositories_listed":3,"syntology":null},{"url":"/paper/simple-unsupervised-keyphrase-extraction","title":"Simple Unsupervised Keyphrase Extraction using Sentence Embeddings","date":"2018-01-13","arxiv_id":"1801.04470","repositories_listed":3,"syntology":null},{"url":"/paper/promptrank-unsupervised-keyphrase-extraction","title":"PromptRank: Unsupervised Keyphrase Extraction Using Prompt","date":"2023-05-08","arxiv_id":"2305.04490","repositories_listed":2,"syntology":null},{"url":"/paper/ucphrase-unsupervised-context-aware-quality","title":"UCPhrase: Unsupervised Context-aware Quality Phrase Tagging","date":"2021-05-28","arxiv_id":"2105.14078","repositories_listed":2,"syntology":null},{"url":"/paper/constrained-abstractive-summarization","title":"Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation","date":"2020-10-24","arxiv_id":"2010.12723","repositories_listed":2,"syntology":null},{"url":"/paper/joint-keyphrase-chunking-and-salience-ranking","title":"Capturing Global Informativeness in Open Domain Keyphrase Extraction","date":"2020-04-28","arxiv_id":"2004.13639","repositories_listed":2,"syntology":null},{"url":"/paper/keyphrase-rubric-relationship-classification","title":"Finding Black Cat in a Coal Cellar -- Keyphrase Extraction & Keyphrase-Rubric Relationship Classification from Complex Assignments","date":"2020-04-03","arxiv_id":"2004.01549","repositories_listed":2,"syntology":null},{"url":"/paper/open-domain-web-keyphrase-extraction-beyond-1","title":"Open Domain Web Keyphrase Extraction Beyond Language Modeling","date":"2019-11-06","arxiv_id":"1911.02671","repositories_listed":2,"syntology":null},{"url":"/paper/complex-network-based-supervised-keyword","title":"Complex Network based Supervised Keyword Extractor","date":"2019-09-26","arxiv_id":"1909.12009","repositories_listed":2,"syntology":null},{"url":"/paper/a-review-of-keyphrase-extraction","title":"A Review of Keyphrase Extraction","date":"2019-05-13","arxiv_id":"1905.05044","repositories_listed":2,"syntology":null},{"url":"/paper/keyphrase-extraction-for-n-best-reranking-in","title":"Keyphrase Extraction for N-best Reranking in Multi-Sentence Compression","date":"2013-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/enhancing-keyphrase-extraction-from-academic-1","title":"Enhancing Keyphrase Extraction from Academic Articles Using Section Structure Information","date":"2025-05-20","arxiv_id":"2505.14149","repositories_listed":1,"syntology":null},{"url":"/paper/longkey-keyphrase-extraction-for-long","title":"LongKey: Keyphrase Extraction for Long Documents","date":"2024-11-26","arxiv_id":"2411.17863","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-keyphrase-ranking-for-relevance","title":"Optimizing Keyphrase Ranking for Relevance and Diversity Using Submodular Function Optimization (SFO)","date":"2024-10-26","arxiv_id":"2410.20080","repositories_listed":1,"syntology":null},{"url":"/paper/chulo-chunk-level-key-information","title":"ChuLo: Chunk-Level Key Information Representation for Long Document Processing","date":"2024-10-14","arxiv_id":"2410.11119","repositories_listed":1,"syntology":null},{"url":"/paper/attention-seeker-dynamic-self-attention","title":"Attention-Seeker: Dynamic Self-Attention Scoring for Unsupervised Keyphrase Extraction","date":"2024-09-17","arxiv_id":"2409.10907","repositories_listed":1,"syntology":null},{"url":"/paper/normy-non-uniform-history-modeling-for-open","title":"NORMY: Non-Uniform History Modeling for Open Retrieval Conversational Question Answering","date":"2024-02-07","arxiv_id":"2402.04548","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-as-zero-shot-keyphrase","title":"Large Language Models as Zero-Shot Keyphrase Extractors: A Preliminary Empirical Study","date":"2023-12-23","arxiv_id":"2312.15156","repositories_listed":1,"syntology":null},{"url":"/paper/bibrank-automatic-keyphrase-extraction","title":"BibRank: Automatic Keyphrase Extraction Platform Using~Metadata","date":"2023-10-13","arxiv_id":"2310.09151","repositories_listed":1,"syntology":null},{"url":"/paper/simckp-simple-contrastive-learning-of","title":"SimCKP: Simple Contrastive Learning of Keyphrase Representations","date":"2023-10-12","arxiv_id":"2310.08221","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-keyphrase-extraction-from-long","title":"Enhancing Keyphrase Extraction from Long Scientific Documents using Graph Embeddings","date":"2023-05-16","arxiv_id":"2305.09316","repositories_listed":1,"syntology":null},{"url":"/paper/kpeval-towards-fine-grained-semantic-based","title":"KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation","date":"2023-03-27","arxiv_id":"2303.15422","repositories_listed":1,"syntology":null},{"url":"/paper/mug-a-general-meeting-understanding-and","title":"MUG: A General Meeting Understanding and Generation Benchmark","date":"2023-03-24","arxiv_id":"2303.13939","repositories_listed":1,"syntology":null},{"url":"/paper/pre-trained-language-models-for-keyphrase","title":"Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study","date":"2022-12-20","arxiv_id":"2212.10233","repositories_listed":1,"syntology":null},{"url":"/paper/patternrank-leveraging-pretrained-language","title":"PatternRank: Leveraging Pretrained Language Models and Part of Speech for Unsupervised Keyphrase Extraction","date":"2022-10-11","arxiv_id":"2210.05245","repositories_listed":1,"syntology":null},{"url":"/paper/query-based-keyphrase-extraction-from-long","title":"Query-Based Keyphrase Extraction from Long Documents","date":"2022-05-11","arxiv_id":"2205.05391","repositories_listed":1,"syntology":null},{"url":"/paper/hyperbolic-relevance-matching-for-neural","title":"Hyperbolic Relevance Matching for Neural Keyphrase Extraction","date":"2022-05-04","arxiv_id":"2205.02047","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-keyphrase-extraction-via-1","title":"Unsupervised Keyphrase Extraction via Interpretable Neural Networks","date":"2022-03-15","arxiv_id":"2203.07640","repositories_listed":1,"syntology":null},{"url":"/paper/topic-aware-contextualized-embeddings-for","title":"Topic Aware Contextualized Embeddings for High Quality Phrase Extraction","date":"2022-01-17","arxiv_id":"2201.10982","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}