{"url":"/sota/word-sense-disambiguation-on-supervised","task":{"name":"Word Sense Disambiguation","url":"/task/word-sense-disambiguation","note":null},"dataset":{"name":"Supervised:","url":"/dataset/word-sense-disambiguation-a-unified"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"The task of Word Sense Disambiguation (WSD) consists of associating words in context with their most suitable entry in a pre-defined sense inventory. The de-facto sense inventory for English in WSD is [WordNet](https://wordnet.princeton.edu)..\r\nFor example, given the word “mouse” and the following sentence:\r\n\r\n“A mouse consists of an object held in one's hand, with one or more buttons.” \r\n\r\nwe would assign “mouse”  with its electronic device sense ([the 4th sense in the WordNet sense inventory](http://wordnetweb.princeton.edu/perl/webwn?c=8&sub=Change&o2=&o0=1&o8=1&o1=1&o7=&o5=&o9=&o6=&o3=&o4=&i=-1&h=000000&s=mouse)).","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Senseval 2","Senseval 3","SemEval 2007","SemEval 2013","SemEval 2015"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Senseval 2":null,"Senseval 3":null,"SemEval 2007":null,"SemEval 2013":null,"SemEval 2015":null}},"counts":{"rows":27,"rows_with_code":16,"rows_with_paper_page":23,"rows_dated":16,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SANDWiCH","metrics":{"SemEval 2007":"80.9","SemEval 2013":"92.6","SemEval 2015":"91.5","Senseval 2":"87.8","Senseval 3":"85.7"},"uses_additional_data":false,"paper_date":"2025-03-07","paper":"/paper/sandwich-semantical-analysis-of-neighbours","paper_url":"https://arxiv.org/abs/2503.05958v1","paper_title":"SANDWiCH: Semantical Analysis of Neighbours for Disambiguating Words in Context ad Hoc","code":"https://github.com/danielguzmanolivares/sandwich","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"GlossGPT","metrics":{"SemEval 2007":"76.2","SemEval 2013":"75.4","SemEval 2015":"83.0","Senseval 2":"86.1","Senseval 3":"82.9"},"uses_additional_data":false,"paper_date":"2025-03-01","paper":"/paper/glossgpt-gpt-for-word-sense-disambiguation","paper_url":"https://www.sciencedirect.com/science/article/pii/S1877050925008385","paper_title":"GlossGPT: GPT for Word Sense Disambiguation using Few-shot Chain-of-Thought Prompting","code":"https://github.com/Sumanathilaka/GlossGPT-GPT-4-WSD-with-COT","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"ConSeC+WNGC","metrics":{"SemEval 2007":"78.5","SemEval 2013":"85.2","SemEval 2015":"87.5","Senseval 2":"82.7","Senseval 3":"81.0"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/consec-word-sense-disambiguation-as","paper_url":"https://aclanthology.org/2021.emnlp-main.112","paper_title":"ConSeC: Word Sense Disambiguation as Continuous Sense Comprehension","code":"https://github.com/sapienzanlp/consec","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"ESR+WNGC","metrics":{"SemEval 2007":"78.5","SemEval 2013":"82.3","SemEval 2015":"85.3","Senseval 2":"82.5","Senseval 3":"80.2"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/improved-word-sense-disambiguation-with","paper_url":"https://aclanthology.org/2021.findings-emnlp.365","paper_title":"Improved Word Sense Disambiguation with Enhanced Sense Representations","code":"https://github.com/nusnlp/esr","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"ConSeC","metrics":{"SemEval 2007":"77.4","SemEval 2013":"83.2","SemEval 2015":"85.2","Senseval 2":"82.3","Senseval 3":"79.9"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/consec-word-sense-disambiguation-as","paper_url":"https://aclanthology.org/2021.emnlp-main.112","paper_title":"ConSeC: Word Sense Disambiguation as Continuous Sense Comprehension","code":"https://github.com/sapienzanlp/consec","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"ESCHER SemCor","metrics":{"SemEval 2007":"76.3","SemEval 2013":"82.2","SemEval 2015":"83.2","Senseval 2":"81.7","Senseval 3":"77.8"},"uses_additional_data":false,"paper_date":"2021-06-01","paper":"/paper/esc-redesigning-wsd-with-extractive-sense","paper_url":"https://aclanthology.org/2021.naacl-main.371","paper_title":"ESC: Redesigning WSD with Extractive Sense Comprehension","code":"https://github.com/SapienzaNLP/esc","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"ESR","metrics":{"SemEval 2007":"77.0","SemEval 2013":"81.5","SemEval 2015":"84.1","Senseval 2":"81.3","Senseval 3":"79.9"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/improved-word-sense-disambiguation-with","paper_url":"https://aclanthology.org/2021.findings-emnlp.365","paper_title":"Improved Word Sense Disambiguation with Enhanced Sense Representations","code":"https://github.com/nusnlp/esr","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"EWISER+WNGC","metrics":{"SemEval 2007":"75.2","SemEval 2013":"80.7","SemEval 2015":"81.8","Senseval 2":"80.8","Senseval 3":"79.0"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/breaking-through-the-80-glass-ceiling-raising","paper_url":"https://aclanthology.org/2020.acl-main.255","paper_title":"Breaking Through the 80\\% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information","code":"https://github.com/SapienzaNLP/ewiser","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"SemCor+WNGC, hypernyms","metrics":{"SemEval 2007":"73.4","SemEval 2013":"78.7","SemEval 2015":"82.6","Senseval 2":"79.7","Senseval 3":"77.8"},"uses_additional_data":false,"paper_date":"2019-05-14","paper":"/paper/sense-vocabulary-compression-through-the","paper_url":"https://arxiv.org/abs/1905.05677v3","paper_title":"Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation","code":"https://github.com/getalp/disambiguate","n_code_links":2,"syntology":null},{"rank_in_archive_order":10,"model":"SparseLMMS+WNGC","metrics":{"SemEval 2007":"73.0","SemEval 2013":"79.4","SemEval 2015":"81.3","Senseval 2":"79.6","Senseval 3":"77.3"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/sparsity-makes-sense-word-sense","paper_url":"https://aclanthology.org/2020.emnlp-main.683","paper_title":"Sparsity Makes Sense: Word Sense Disambiguation Using Sparse Contextualized Word Representations","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"BEM","metrics":{"SemEval 2007":"74.5","SemEval 2013":"79.7","SemEval 2015":"81.7","Senseval 2":"79.4","Senseval 3":"77.4"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/moving-down-the-long-tail-of-word-sense-1","paper_url":"https://aclanthology.org/2020.acl-main.95","paper_title":"Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"EWISER","metrics":{"SemEval 2007":"71.0","SemEval 2013":"78.9","SemEval 2015":"79.3","Senseval 2":"78.9","Senseval 3":"78.4"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/breaking-through-the-80-glass-ceiling-raising","paper_url":"https://aclanthology.org/2020.acl-main.255","paper_title":"Breaking Through the 80\\% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information","code":"https://github.com/SapienzaNLP/ewiser","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"ARES","metrics":{"SemEval 2007":"71.0","SemEval 2013":"77.3","SemEval 2015":"83.2","Senseval 2":"78.0","Senseval 3":"77.1"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/with-more-contexts-comes-better-performance","paper_url":"https://aclanthology.org/2020.emnlp-main.285","paper_title":"With More Contexts Comes Better Performance: Contextualized Sense Embeddings for All-Round Word Sense Disambiguation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"SparseLMMS","metrics":{"SemEval 2007":"68.8","SemEval 2013":"76.1","SemEval 2015":"77.5","Senseval 2":"77.9","Senseval 3":"77.8"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/sparsity-makes-sense-word-sense","paper_url":"https://aclanthology.org/2020.emnlp-main.683","paper_title":"Sparsity Makes Sense: Word Sense Disambiguation Using Sparse Contextualized Word Representations","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"GlossBERT","metrics":{"SemEval 2007":"72.5","SemEval 2013":"76.1","SemEval 2015":"80.4","Senseval 2":"77.7","Senseval 3":"75.2"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/glossbert-bert-for-word-sense-disambiguation","paper_url":"https://arxiv.org/abs/1908.07245v4","paper_title":"GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge","code":"https://github.com/HSLCY/GlossBERT","n_code_links":3,"syntology":null},{"rank_in_archive_order":16,"model":"BERT (linear projection)","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,"paper_date":"2019-10-01","paper":"/paper/improved-word-sense-disambiguation-using-pre","paper_url":"https://arxiv.org/abs/1910.00194v2","paper_title":"Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations","code":"https://github.com/nusnlp/contextemb-wsd","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"SemCor+WNGT, vocabulary reduced, ensemble","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,"paper_date":"2018-11-02","paper":"/paper/improving-the-coverage-and-the-generalization","paper_url":"http://arxiv.org/abs/1811.00960v1","paper_title":"Improving the Coverage and the Generalization Ability of Neural Word Sense Disambiguation through Hypernymy and Hyponymy Relationships","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"BERT (nearest neighbour)","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,"paper_date":"2019-10-01","paper":"/paper/improved-word-sense-disambiguation-using-pre","paper_url":"https://arxiv.org/abs/1910.00194v2","paper_title":"Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations","code":"https://github.com/nusnlp/contextemb-wsd","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"supWSD<sub>emb</sub>","metrics":{"SemEval 2007":"63.1","SemEval 2013":"66.8","SemEval 2015":"71.8","Senseval 2":"72.7","Senseval 3":"70.6"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"GAS<sub>ext</sub>","metrics":{"SemEval 2007":"--*","SemEval 2013":"67.2","SemEval 2015":"72.6","Senseval 2":"72.2","Senseval 3":"70.5"},"uses_additional_data":false,"paper_date":"2018-05-21","paper":"/paper/incorporating-glosses-into-neural-word-sense","paper_url":"http://arxiv.org/abs/1805.08028v2","paper_title":"Incorporating Glosses into Neural Word Sense Disambiguation","code":"https://github.com/jimiyulu/WSD_MemNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"GAS","metrics":{"SemEval 2007":"--*","SemEval 2013":"66.7","SemEval 2015":"71.6","Senseval 2":"72.0","Senseval 3":"70.0"},"uses_additional_data":false,"paper_date":"2018-05-21","paper":"/paper/incorporating-glosses-into-neural-word-sense","paper_url":"http://arxiv.org/abs/1805.08028v2","paper_title":"Incorporating Glosses into Neural Word Sense Disambiguation","code":"https://github.com/jimiyulu/WSD_MemNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"Bi-LSTM<sub>att+LEX</sub>","metrics":{"SemEval 2007":"63.7*","SemEval 2013":"66.4","SemEval 2015":"72.4","Senseval 2":"72.0","Senseval 3":"69.4"},"uses_additional_data":false,"paper_date":"2017-09-01","paper":"/paper/neural-sequence-learning-models-for-word","paper_url":"https://aclanthology.org/D17-1120","paper_title":"Neural Sequence Learning Models for Word Sense Disambiguation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"Bi-LSTM<sub>att+LEX+POS</sub>","metrics":{"SemEval 2007":"64.8*","SemEval 2013":"66.9","SemEval 2015":"71.5","Senseval 2":"72.0","Senseval 3":"69.1"},"uses_additional_data":false,"paper_date":"2017-09-01","paper":"/paper/neural-sequence-learning-models-for-word","paper_url":"https://aclanthology.org/D17-1120","paper_title":"Neural Sequence Learning Models for Word Sense Disambiguation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"context2vec","metrics":{"SemEval 2007":"61.3","SemEval 2013":"65.6","SemEval 2015":"71.9","Senseval 2":"71.8","Senseval 3":"69.1"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"ELMo","metrics":{"SemEval 2007":"62.2","SemEval 2013":"66.2","SemEval 2015":"71.3","Senseval 2":"71.6","Senseval 3":"69.6"},"uses_additional_data":false,"paper_date":"2018-02-15","paper":"/paper/deep-contextualized-word-representations","paper_url":"http://arxiv.org/abs/1802.05365v2","paper_title":"Deep contextualized word representations","code":"https://github.com/flairNLP/flair","n_code_links":46,"syntology":{"n_ran":23,"n_unverified":35,"n_samples":58,"n_pointer_only_licence":25}},{"rank_in_archive_order":26,"model":"supWSD","metrics":{"SemEval 2007":"60.2","SemEval 2013":"65.8","SemEval 2015":"70.0","Senseval 2":"71.3","Senseval 3":"68.8"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"MFS baseline","metrics":{"SemEval 2007":"54.5","SemEval 2013":"63.8","SemEval 2015":"67.1","Senseval 2":"65.6","Senseval 3":"66.0"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":23,"n_unverified":37,"n_samples":60,"n_pointer_only_licence":25,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":23,"n_unverified":37,"n_samples":60,"n_pointer_only_licence":25,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}