{"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/integrating-weakly-supervised-word-sense","title":"Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation","arxiv_id":"1810.02614","date":"2018-10-05","proceeding":"TACL 2018 1","authors":["Xiao Pu","Nikolaos Pappas","James Henderson","Andrei Popescu-Belis"],"abstract":"This paper demonstrates that word sense disambiguation (WSD) can improve\nneural machine translation (NMT) by widening the source context considered when\nmodeling the senses of potentially ambiguous words. We first introduce three\nadaptive clustering algorithms for WSD, based on k-means, Chinese restaurant\nprocesses, and random walks, which are then applied to large word contexts\nrepresented in a low-rank space and evaluated on SemEval shared-task data. We\nthen learn word vectors jointly with sense vectors defined by our best WSD\nmethod, within a state-of-the-art NMT system. We show that the concatenation of\nthese vectors, and the use of a sense selection mechanism based on the weighted\naverage of sense vectors, outperforms several baselines including sense-aware\nones. This is demonstrated by translation on five language pairs. The\nimprovements are above one BLEU point over strong NMT baselines, +4% accuracy\nover all ambiguous nouns and verbs, or +20% when scored manually over several\nchallenging words.","url_abs":"http://arxiv.org/abs/1810.02614v1","url_pdf":"http://arxiv.org/pdf/1810.02614v1.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":"integrating-weakly-supervised-word-sense","repo_url":"https://github.com/idiap/sense_aware_NMT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-sense-disambiguation","task_name":"Word Sense Disambiguation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.02614","atlas_url":"https://app.syntology.ai/?focus=1810.02614","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}