{"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/muse-modularizing-unsupervised-sense","title":"MUSE: Modularizing Unsupervised Sense Embeddings","arxiv_id":"1704.04601","date":"2017-04-15","proceeding":"EMNLP 2017 9","authors":["Guang-He Lee","Yun-Nung Chen"],"abstract":"This paper proposes to address the word sense ambiguity issue in an\nunsupervised manner, where word sense representations are learned along a word\nsense selection mechanism given contexts. Prior work focused on designing a\nsingle model to deliver both mechanisms, and thus suffered from either\ncoarse-grained representation learning or inefficient sense selection. The\nproposed modular approach, MUSE, implements flexible modules to optimize\ndistinct mechanisms, achieving the first purely sense-level representation\nlearning system with linear-time sense selection. We leverage reinforcement\nlearning to enable joint training on the proposed modules, and introduce\nvarious exploration techniques on sense selection for better robustness. The\nexperiments on benchmark data show that the proposed approach achieves the\nstate-of-the-art performance on synonym selection as well as on contextual word\nsimilarities in terms of MaxSimC.","url_abs":"http://arxiv.org/abs/1704.04601v2","url_pdf":"http://arxiv.org/pdf/1704.04601v2.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":"muse-modularizing-unsupervised-sense","repo_url":"https://github.com/MiuLab/MUSE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}