{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/patternrank-leveraging-pretrained-language","title":"PatternRank: Leveraging Pretrained Language Models and Part of Speech for Unsupervised Keyphrase Extraction","arxiv_id":"2210.05245","date":"2022-10-11","proceeding":null,"authors":["Tim Schopf","Simon Klimek","Florian Matthes"],"abstract":"Keyphrase extraction is the process of automatically selecting a small set of most relevant phrases from a given text. Supervised keyphrase extraction approaches need large amounts of labeled training data and perform poorly outside the domain of the training data. In this paper, we present PatternRank, which leverages pretrained language models and part-of-speech for unsupervised keyphrase extraction from single documents. Our experiments show PatternRank achieves higher precision, recall and F1-scores than previous state-of-the-art approaches. In addition, we present the KeyphraseVectorizers package, which allows easy modification of part-of-speech patterns for candidate keyphrase selection, and hence adaptation of our approach to any domain.","url_abs":"https://arxiv.org/abs/2210.05245v2","url_pdf":"https://arxiv.org/pdf/2210.05245v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"patternrank-leveraging-pretrained-language","repo_url":"https://github.com/timschopf/keyphrasevectorizers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"keyphrase-extraction","task_name":"Keyphrase Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keyphrase-extraction-on-inspec","task":"Keyphrase Extraction","dataset":"Inspec","model":"PatternRank","rank_in_archive_order":3,"of":3,"metrics":{"F1@10":"30.99"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}