{"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/a-simple-approach-to-learn-polysemous-word","title":"A Simple Approach to Learn Polysemous Word Embeddings","arxiv_id":"1707.01793","date":"2017-07-06","proceeding":null,"authors":["Yifan Sun","Nikhil Rao","Weicong Ding"],"abstract":"Many NLP applications require disambiguating polysemous words. Existing\nmethods that learn polysemous word vector representations involve first\ndetecting various senses and optimizing the sense-specific embeddings\nseparately, which are invariably more involved than single sense learning\nmethods such as word2vec. Evaluating these methods is also problematic, as\nrigorous quantitative evaluations in this space is limited, especially when\ncompared with single-sense embeddings. In this paper, we propose a simple\nmethod to learn a word representation, given any context. Our method only\nrequires learning the usual single sense representation, and coefficients that\ncan be learnt via a single pass over the data. We propose several new test sets\nfor evaluating word sense induction, relevance detection, and contextual word\nsimilarity, significantly supplementing the currently available tests. Results\non these and other tests show that while our method is embarrassingly simple,\nit achieves excellent results when compared to the state of the art models for\nunsupervised polysemous word representation learning.","url_abs":"http://arxiv.org/abs/1707.01793v2","url_pdf":"http://arxiv.org/pdf/1707.01793v2.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":"a-simple-approach-to-learn-polysemous-word","repo_url":"https://github.com/dingwc/multisense","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"a-simple-approach-to-learn-polysemous-word","repo_url":"https://github.com/SagarDollin/unsupervised_WSD_on_top_of_word2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"relevance-detection","task_name":"Relevance Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"word-sense-induction","task_name":"Word Sense Induction"},{"task_slug":"word-similarity","task_name":"Word Similarity"}],"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}