{"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/improving-the-coverage-and-the-generalization","title":"Improving the Coverage and the Generalization Ability of Neural Word Sense Disambiguation through Hypernymy and Hyponymy Relationships","arxiv_id":"1811.00960","date":"2018-11-02","proceeding":null,"authors":["Loïc Vial","Benjamin Lecouteux","Didier Schwab"],"abstract":"In Word Sense Disambiguation (WSD), the predominant approach generally\ninvolves a supervised system trained on sense annotated corpora. The limited\nquantity of such corpora however restricts the coverage and the performance of\nthese systems. In this article, we propose a new method that solves these\nissues by taking advantage of the knowledge present in WordNet, and especially\nthe hypernymy and hyponymy relationships between synsets, in order to reduce\nthe number of different sense tags that are necessary to disambiguate all words\nof the lexical database. Our method leads to state of the art results on most\nWSD evaluation tasks, while improving the coverage of supervised systems,\nreducing the training time and the size of the models, without additional\ntraining data. In addition, we exhibit results that significantly outperform\nthe state of the art when our method is combined with an ensembling technique\nand the addition of the WordNet Gloss Tagged as training corpus.","url_abs":"http://arxiv.org/abs/1811.00960v1","url_pdf":"http://arxiv.org/pdf/1811.00960v1.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":[],"tasks":[{"task_slug":"word-sense-disambiguation","task_name":"Word Sense Disambiguation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/word-sense-disambiguation-on-semeval-2007","task":"Word Sense Disambiguation","dataset":"SemEval 2007 Task 17","model":"SemCor+WNGT, vocabulary reduced, ensemble","rank_in_archive_order":2,"of":9,"metrics":{"F1":"66.81"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-semeval-2007-1","task":"Word Sense Disambiguation","dataset":"SemEval 2007 Task 7","model":"SemCor+WNGT, vocabulary reduced, ensemble","rank_in_archive_order":2,"of":10,"metrics":{"F1":"86.02"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-semeval-2013","task":"Word Sense Disambiguation","dataset":"SemEval 2013 Task 12","model":"SemCor+WNGT, vocabulary reduced, ensemble","rank_in_archive_order":2,"of":12,"metrics":{"F1":"72.63"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-semeval-2015","task":"Word Sense Disambiguation","dataset":"SemEval 2015 Task 13","model":"SemCor+WNGT, vocabulary reduced, ensemble","rank_in_archive_order":2,"of":6,"metrics":{"F1":"74.46"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-senseval-2","task":"Word Sense Disambiguation","dataset":"SensEval 2","model":"SemCor+WNGT, vocabulary reduced, ensemble","rank_in_archive_order":2,"of":11,"metrics":{"F1":"75.15"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-senseval-3-task","task":"Word Sense Disambiguation","dataset":"SensEval 3 Task 1","model":"SemCor+WNGT, vocabulary reduced, ensemble","rank_in_archive_order":7,"of":11,"metrics":{"F1":"70.11"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-supervised","task":"Word Sense Disambiguation","dataset":"Supervised:","model":"SemCor+WNGT, vocabulary reduced, ensemble","rank_in_archive_order":17,"of":27,"metrics":{"SemEval 2007":"66.81","SemEval 2013":"72.63","SemEval 2015":"74.46","Senseval 2":"75.15","Senseval 3":"70.11"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.00960","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}