{"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/towards-a-seamless-integration-of-word-senses","title":"Towards a Seamless Integration of Word Senses into Downstream NLP Applications","arxiv_id":"1710.06632","date":"2017-10-18","proceeding":"ACL 2017 7","authors":["Mohammad Taher Pilehvar","Jose Camacho-Collados","Roberto Navigli","Nigel Collier"],"abstract":"Lexical ambiguity can impede NLP systems from accurate understanding of\nsemantics. Despite its potential benefits, the integration of sense-level\ninformation into NLP systems has remained understudied. By incorporating a\nnovel disambiguation algorithm into a state-of-the-art classification model, we\ncreate a pipeline to integrate sense-level information into downstream NLP\napplications. We show that a simple disambiguation of the input text can lead\nto consistent performance improvement on multiple topic categorization and\npolarity detection datasets, particularly when the fine granularity of the\nunderlying sense inventory is reduced and the document is sufficiently large.\nOur results also point to the need for sense representation research to focus\nmore on in vivo evaluations which target the performance in downstream NLP\napplications rather than artificial benchmarks.","url_abs":"http://arxiv.org/abs/1710.06632v1","url_pdf":"http://arxiv.org/pdf/1710.06632v1.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":"towards-a-seamless-integration-of-word-senses","repo_url":"https://github.com/pilehvar/sensecnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1710.06632","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}