{"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/retrofitting-word-vectors-to-semantic","title":"Retrofitting Word Vectors to Semantic Lexicons","arxiv_id":"1411.4166","date":"2014-11-15","proceeding":"HLT 2015 5","authors":["Manaal Faruqui","Jesse Dodge","Sujay K. Jauhar","Chris Dyer","Eduard Hovy","Noah A. Smith"],"abstract":"Vector space word representations are learned from distributional information\nof words in large corpora. Although such statistics are semantically\ninformative, they disregard the valuable information that is contained in\nsemantic lexicons such as WordNet, FrameNet, and the Paraphrase Database. This\npaper proposes a method for refining vector space representations using\nrelational information from semantic lexicons by encouraging linked words to\nhave similar vector representations, and it makes no assumptions about how the\ninput vectors were constructed. Evaluated on a battery of standard lexical\nsemantic evaluation tasks in several languages, we obtain substantial\nimprovements starting with a variety of word vector models. Our refinement\nmethod outperforms prior techniques for incorporating semantic lexicons into\nthe word vector training algorithms.","url_abs":"http://arxiv.org/abs/1411.4166v4","url_pdf":"http://arxiv.org/pdf/1411.4166v4.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":"retrofitting-word-vectors-to-semantic","repo_url":"https://github.com/mfaruqui/retrofitting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"retrofitting-word-vectors-to-semantic","repo_url":"https://github.com/SfS-ASCL/GermanetEmbeddings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1411.4166","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}