{"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/counter-fitting-word-vectors-to-linguistic","title":"Counter-fitting Word Vectors to Linguistic Constraints","arxiv_id":"1603.00892","date":"2016-03-02","proceeding":"NAACL 2016 6","authors":["Nikola Mrkšić","Diarmuid Ó Séaghdha","Blaise Thomson","Milica Gašić","Lina Rojas-Barahona","Pei-Hao Su","David Vandyke","Tsung-Hsien Wen","Steve Young"],"abstract":"In this work, we present a novel counter-fitting method which injects\nantonymy and synonymy constraints into vector space representations in order to\nimprove the vectors' capability for judging semantic similarity. Applying this\nmethod to publicly available pre-trained word vectors leads to a new state of\nthe art performance on the SimLex-999 dataset. We also show how the method can\nbe used to tailor the word vector space for the downstream task of dialogue\nstate tracking, resulting in robust improvements across different dialogue\ndomains.","url_abs":"http://arxiv.org/abs/1603.00892v1","url_pdf":"http://arxiv.org/pdf/1603.00892v1.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":"counter-fitting-word-vectors-to-linguistic","repo_url":"https://github.com/nmrksic/counter-fitting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"counter-fitting-word-vectors-to-linguistic","repo_url":"https://github.com/lrank/Linguistic_adversity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dialogue-state-tracking","task_name":"Dialogue State Tracking"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.00892","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}