{"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/improved-word-sense-disambiguation-using-pre","title":"Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations","arxiv_id":"1910.00194","date":"2019-10-01","proceeding":"IJCNLP 2019 11","authors":["Christian Hadiwinoto","Hwee Tou Ng","Wee Chung Gan"],"abstract":"Contextualized word representations are able to give different representations for the same word in different contexts, and they have been shown to be effective in downstream natural language processing tasks, such as question answering, named entity recognition, and sentiment analysis. However, evaluation on word sense disambiguation (WSD) in prior work shows that using contextualized word representations does not outperform the state-of-the-art approach that makes use of non-contextualized word embeddings. In this paper, we explore different strategies of integrating pre-trained contextualized word representations and our best strategy achieves accuracies exceeding the best prior published accuracies by significant margins on multiple benchmark WSD datasets. We make the source code available at https://github.com/nusnlp/contextemb-wsd.","url_abs":"https://arxiv.org/abs/1910.00194v2","url_pdf":"https://arxiv.org/pdf/1910.00194v2.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":"improved-word-sense-disambiguation-using-pre","repo_url":"https://github.com/nusnlp/contextemb-wsd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"word-sense-disambiguation","task_name":"Word Sense Disambiguation"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/word-sense-disambiguation-on-supervised","task":"Word Sense Disambiguation","dataset":"Supervised:","model":"BERT (linear projection)","rank_in_archive_order":16,"of":27,"metrics":{"SemEval 2007":"68.1","SemEval 2013":"71.1","SemEval 2015":"76.2","Senseval 2":"75.5","Senseval 3":"73.6"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-supervised","task":"Word Sense Disambiguation","dataset":"Supervised:","model":"BERT (nearest neighbour)","rank_in_archive_order":18,"of":27,"metrics":{"SemEval 2007":"63.3","SemEval 2013":"69.2","SemEval 2015":"74.4","Senseval 2":"73.8","Senseval 3":"71.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.00194","atlas_url":"https://app.syntology.ai/?focus=1910.00194","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}