{"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/learning-topic-sensitive-word-representations","title":"Learning Topic-Sensitive Word Representations","arxiv_id":"1705.00441","date":"2017-05-01","proceeding":"ACL 2017 7","authors":["Marzieh Fadaee","Arianna Bisazza","Christof Monz"],"abstract":"Distributed word representations are widely used for modeling words in NLP\ntasks. Most of the existing models generate one representation per word and do\nnot consider different meanings of a word. We present two approaches to learn\nmultiple topic-sensitive representations per word by using Hierarchical\nDirichlet Process. We observe that by modeling topics and integrating topic\ndistributions for each document we obtain representations that are able to\ndistinguish between different meanings of a given word. Our models yield\nstatistically significant improvements for the lexical substitution task\nindicating that commonly used single word representations, even when combined\nwith contextual information, are insufficient for this task.","url_abs":"http://arxiv.org/abs/1705.00441v1","url_pdf":"http://arxiv.org/pdf/1705.00441v1.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":"learning-topic-sensitive-word-representations","repo_url":"https://github.com/marziehf/TS_Embeddings","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}