{"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/word-sense-disambiguation-using-a","title":"Word Sense Disambiguation using a Bidirectional LSTM","arxiv_id":"1606.03568","date":"2016-06-11","proceeding":"WS 2016 12","authors":["Mikael Kågebäck","Hans Salomonsson"],"abstract":"In this paper we present a clean, yet effective, model for word sense\ndisambiguation. Our approach leverage a bidirectional long short-term memory\nnetwork which is shared between all words. This enables the model to share\nstatistical strength and to scale well with vocabulary size. The model is\ntrained end-to-end, directly from the raw text to sense labels, and makes\neffective use of word order. We evaluate our approach on two standard datasets,\nusing identical hyperparameter settings, which are in turn tuned on a third set\nof held out data. We employ no external resources (e.g. knowledge graphs,\npart-of-speech tagging, etc), language specific features, or hand crafted\nrules, but still achieve statistically equivalent results to the best\nstate-of-the-art systems, that employ no such limitations.","url_abs":"http://arxiv.org/abs/1606.03568v2","url_pdf":"http://arxiv.org/pdf/1606.03568v2.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":"word-sense-disambiguation-using-a","repo_url":"https://bitbucket.org/salomons/wsd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"word-sense-disambiguation","task_name":"Word Sense Disambiguation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/word-sense-disambiguation-on-senseval-2-1","task":"Word Sense Disambiguation","dataset":"SensEval 2 Lexical Sample","model":"BiLSTM with GloVe","rank_in_archive_order":2,"of":3,"metrics":{"F1":"66.9"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-senseval-3","task":"Word Sense Disambiguation","dataset":"SensEval 3 Lexical Sample","model":"BiLSTM with GloVe","rank_in_archive_order":2,"of":4,"metrics":{"F1":"73.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.03568","atlas_url":"https://app.syntology.ai/?focus=1606.03568","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}