{"url":"/task/word-sense-induction","name":"Word Sense Induction","slug":"word-sense-induction","description_markdown":"Word sense induction (WSI) is widely known as the “unsupervised version” of WSD. The problem states as: Given a target word (e.g., “cold”) and a collection of sentences (e.g., “I caught a cold”, “The weather is cold”) that use the word, cluster the sentences according to their different senses/meanings. We do not need to know the sense/meaning of each cluster, but sentences inside a cluster should have used the target words with the same sense.\r\n\r\nDescription from [NLP Progress](http://nlpprogress.com/english/word_sense_disambiguation.html)","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":107,"papers_with_code":19,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/word-sense-induction-on-semeval-2010-wsi-1","slug":"word-sense-induction-on-semeval-2010-wsi-1","dataset":"SemEval 2010 WSI","dataset_url":null,"rows_in_archive":5,"metrics":["F-Score","V-Measure","AVG"],"first_row_in_archive_order":{"model":"BERT+DP","paper_title":"Towards better substitution-based word sense induction","paper_url":"/paper/towards-better-substitution-based-word-sense","paper_date":"2019-05-29","arxiv_id":"1905.12598","code_links":[{"title":"asafamr/bertwsi","url":"https://github.com/asafamr/bertwsi"},{"title":"lucy3/bertwsi","url":"https://github.com/lucy3/bertwsi"}],"syntology":null}}],"datasets":[{"url":"/dataset/brwac","name":"BRWAC","full_name":"","num_papers_in_archive":17}],"subtasks":[],"parent_tasks":[{"url":"/task/word-sense-disambiguation","name":"Word Sense Disambiguation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":19,"of":19,"tagged_in_all":107,"items":[{"url":"/paper/breaking-sticks-and-ambiguities-with-adaptive","title":"Breaking Sticks and Ambiguities with Adaptive Skip-gram","date":"2015-02-25","arxiv_id":"1502.07257","repositories_listed":3,"syntology":null},{"url":"/paper/rudsi-graph-based-word-sense-induction","title":"RuDSI: graph-based word sense induction dataset for Russian","date":"2022-09-28","arxiv_id":"2209.13750","repositories_listed":2,"syntology":null},{"url":"/paper/towards-better-substitution-based-word-sense","title":"Towards better substitution-based word sense induction","date":"2019-05-29","arxiv_id":"1905.12598","repositories_listed":2,"syntology":null},{"url":"/paper/a-simple-approach-to-learn-polysemous-word","title":"A Simple Approach to Learn Polysemous Word Embeddings","date":"2017-07-06","arxiv_id":"1707.01793","repositories_listed":2,"syntology":null},{"url":"/paper/a-systematic-comparison-of-contextualized","title":"A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change","date":"2024-02-19","arxiv_id":"2402.12011","repositories_listed":1,"syntology":null},{"url":"/paper/words-as-gatekeepers-measuring-discipline","title":"Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications","date":"2022-12-19","arxiv_id":"2212.09676","repositories_listed":1,"syntology":null},{"url":"/paper/always-keep-your-target-in-mind-studying-1","title":"Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution","date":"2022-06-07","arxiv_id":"2206.11815","repositories_listed":1,"syntology":null},{"url":"/paper/polylm-learning-about-polysemy-through","title":"PolyLM: Learning about Polysemy through Language Modeling","date":"2021-01-25","arxiv_id":"2101.10448","repositories_listed":1,"syntology":null},{"url":"/paper/an-evaluation-method-for-diachronic-word","title":"An Evaluation Method for Diachronic Word Sense Induction","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/how-does-bert-capture-semantics-a-closer-look","title":"How does BERT capture semantics? A closer look at polysemous words","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/uob-at-semeval-2020-task-1-automatic","title":"UoB at SemEval-2020 Task 1: Automatic Identification of Novel Word Senses","date":"2020-10-18","arxiv_id":"2010.09072","repositories_listed":1,"syntology":null},{"url":"/paper/autosense-model-for-word-sense-induction","title":"AutoSense Model for Word Sense Induction","date":"2018-11-22","arxiv_id":"1811.09242","repositories_listed":1,"syntology":null},{"url":"/paper/word-sense-induction-with-neural-bilm-and","title":"Word Sense Induction with Neural biLM and Symmetric Patterns","date":"2018-08-26","arxiv_id":"1808.08518","repositories_listed":1,"syntology":null},{"url":"/paper/russian-word-sense-induction-by-clustering","title":"Russian word sense induction by clustering averaged word embeddings","date":"2018-05-06","arxiv_id":"1805.02258","repositories_listed":1,"syntology":null},{"url":"/paper/improved-word-representation-learning-with","title":"Improved Word Representation Learning with Sememes","date":"2017-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/watset-automatic-induction-of-synsets-from-a","title":"Watset: Automatic Induction of Synsets from a Graph of Synonyms","date":"2017-04-24","arxiv_id":"1704.07157","repositories_listed":1,"syntology":null},{"url":"/paper/automated-wordnet-construction-using-word","title":"Automated WordNet Construction Using Word Embeddings","date":"2017-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unimelb-topic-modelling-based-word-sense-1","title":"unimelb: Topic Modelling-based Word Sense Induction","date":"2013-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-topic-coherence-over-many-models","title":"Exploring Topic Coherence over Many Models and Many Topics","date":"2012-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}