--- title: "Unsupervised Word Sense Disambiguation — Yarowsky 1995" description: "The paper addresses word sense disambiguation: choosing which dictionary sense an ambiguous English word has in a given context, without expensive…" authors: ["David Yarowsky"] year: 1995 venue: "33rd Annual Meeting of the Association for Computational Linguistics" source: "https://aclanthology.org/P95-1026/" doi: "10.3115/981658.981684" licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/yarowsky-1995-unsupervised-word-sense-disambiguation-rivaling/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yarowsky-1995-unsupervised-word-sense-disambiguation-rivaling/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [1995](https://md.research.elamur.ai/free/en/papers/1995/) / Unsupervised Word Sense Disambiguation Rivaling Supervised Methods # Unsupervised Word Sense Disambiguation Rivaling Supervised Methods **Authors:** [David Yarowsky](https://md.research.elamur.ai/free/en/authors/david-yarowsky/) · **Year:** 1995 · **Venue:** 33rd Annual Meeting of the Association for Computational Linguistics · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/) **Links:** [Publisher's page](https://aclanthology.org/P95-1026/) · [PDF](https://aclanthology.org/P95-1026.pdf) · [DOI 10.3115/981658.981684](https://doi.org/10.3115/981658.981684) · [OpenAlex](https://openalex.org/W2101210369) **Citations:** 2385 citations (openalex-snapshot · 2026-10-14) · [455](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary The paper addresses word sense disambiguation: choosing which dictionary sense an ambiguous English word has in a given context, without expensive hand-labelled training data. Yarowsky relies on two regularities of language. First, a word rarely switches sense within one document. Second, nearby words (collocations) are strong and consistent signals of sense. The method starts with a few seed collocations for each sense, such as *life* versus *manufacturing* for *plant*, and uses them to label a small part of an untagged corpus. It then trains a decision-list classifier, with evidence ranked by log-likelihood ratio, and applies it to the remaining examples. Each round adds the confidently labelled cases to the training set. A soft document-level constraint spreads and corrects labels. Tested on a set of ambiguous words, this bootstrapping reaches over 96% accuracy. That is roughly equal to a supervised decision list trained on the same contexts and better than Schütze's clustering-based unsupervised method. The work showed that raw text alone can give near-supervised results, and it became a standard template for self-training in NLP. ## Key points - The "one sense per discourse" hypothesis was checked on 37,232 hand-tagged examples. When a word appears more than once in a document, it keeps the majority sense about 99.8% of the time. The constraint applies in about 50.1% of cases. - For adjacent content words, "one sense per collocation" is reliable more than 97% of the time. It weakens as the distance between words grows and is weaker for function words. - In the worked example for *plant* (7,538 instances), the initial seeds labelled only about 2% of the data. The other roughly 98% started out unlabelled. - The unsupervised system scored 95.5% versus 96.1% for the supervised one. With the discourse constraint added, it reached 96.5% and beat the supervised baseline. - On the same 4 words, it outperformed Schütze's unsupervised algorithm, 96.7% versus 92.2%, even though Schütze's data had a higher baseline. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [AI & machine learning](https://md.research.elamur.ai/free/en/shelves/ai/) Topics: [Word sense disambiguation](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/) ## Cited by Cited by 455 papers of our library cite it (of the 140673 whose bibliographies we read); 33 of them have a page here, 422 not yet. - [Scaling to Very Very Large Corpora for Natural Language Disambiguation](https://md.research.elamur.ai/free/en/papers/banko-2001-scaling-very-very-large-corpora/) - [Extracting Paraphrases from a Parallel Corpus](https://md.research.elamur.ai/free/en/papers/barzilay-2001-extracting-paraphrases-parallel-corpus/) - [Combining Labeled and Unlabeled Data with Co-Training](https://md.research.elamur.ai/free/en/papers/blum-1998-combining-labeled-unlabeled-data-co-training/) - [Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks](https://md.research.elamur.ai/free/en/papers/chen-2015-event-extraction-dynamic-multi-pooling/) - [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://md.research.elamur.ai/free/en/papers/chen-2023-empirical-survey-data-augmentation-limited/) - [Semi-Supervised Sequence Modeling with Cross-View Training](https://md.research.elamur.ai/free/en/papers/clark-2018-semi-supervised-sequence-modeling-cross/) - [Unsupervised Models for Named Entity Classification](https://md.research.elamur.ai/free/en/papers/collins-1999-unsupervised-models-named-entity-classification/) - [An IR Approach for Translating New Words from Nonparallel, Comparable Texts](https://md.research.elamur.ai/free/en/papers/fung-1998-ir-approach-translating-new-words/) - [Reinforced Self-Training (ReST) for Language Modeling](https://md.research.elamur.ai/free/en/papers/gulcehre-2023-reinforced-self-training-rest-language/) - [Learning Bilingual Lexicons from Monolingual Corpora](https://md.research.elamur.ai/free/en/papers/haghighi-2008-learning-bilingual-lexicons-monolingual-corpora/) - [Using Cross-Entity Inference to Improve Event Extraction](https://md.research.elamur.ai/free/en/papers/hong-2011-cross-entity-inference-improve-event/) - [Introduction to the Special Issue on Word Sense Disambiguation: The State of the Art](https://md.research.elamur.ai/free/en/papers/ide-1998-introduction-special-issue-word-sense/) - [Refining Event Extraction through Cross-Document Inference](https://md.research.elamur.ai/free/en/papers/ji-2008-refining-event-extraction-through-cross/) - [Joint Entity and Event Coreference Resolution across Documents](https://md.research.elamur.ai/free/en/papers/lee-2012-joint-entity-event-coreference-resolution/) - [Discourse Relation Prediction and Discourse Parsing in Dialogues with Minimal Supervision](https://md.research.elamur.ai/free/en/papers/li-2024-discourse-relation-prediction-discourse-parsing/) - [Using Document Level Cross-Event Inference to Improve Event Extraction](https://md.research.elamur.ai/free/en/papers/liao-2010-document-level-cross-event-inference/) - [Leveraging FrameNet to Improve Automatic Event Detection](https://md.research.elamur.ai/free/en/papers/liu-2016-leveraging-framenet-improve-automatic-event/) - [Weakly Supervised Learning for Hedge Classification in Scientific Literature](https://md.research.elamur.ai/free/en/papers/medlock-2007-weakly-supervised-learning-hedge-classification/) - [Augmented Language Models: a Survey](https://md.research.elamur.ai/free/en/papers/mialon-2023-augmented-language-models-survey/) - [Name Tagging with Word Clusters and Discriminative Training](https://md.research.elamur.ai/free/en/papers/miller-2004-name-tagging-word-clusters-discriminative/) - [Integrating Multiple Knowledge Sources to Disambiguate Word Sense: An Exemplar-Based Approach](https://md.research.elamur.ai/free/en/papers/ng-1996-integrating-multiple-knowledge-sources-disambiguate/) - [Bootstrapping Coreference Classifiers with Multiple Machine Learning Algorithms](https://md.research.elamur.ai/free/en/papers/ng-2003-bootstrapping-coreference-classifiers-multiple-machine/) - [Semantic Class Induction and Coreference Resolution](https://md.research.elamur.ai/free/en/papers/ng-2007-semantic-class-induction-coreference-resolution/) - [The Web as a Parallel Corpus](https://md.research.elamur.ai/free/en/papers/resnik-2003-web-as-parallel-corpus/) - [Named Entity Recognition in Tweets: An Experimental Study](https://md.research.elamur.ai/free/en/papers/ritter-2011-named-entity-recognition-tweets-experimental/) - [Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference](https://md.research.elamur.ai/free/en/papers/schick-2021-exploiting-cloze-questions-few-shot/) - [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/schick-2021-it-s-not-just-size/) - [Toolformer: Language Models Can Teach Themselves to Use Tools](https://md.research.elamur.ai/free/en/papers/schick-2023-toolformer-language-models-can-teach/) - [Automatic Word Sense Discrimination](https://md.research.elamur.ai/free/en/papers/schutze-1998-automatic-word-sense-discrimination/) - [Active Learning Literature Survey](https://md.research.elamur.ai/free/en/papers/settles-2009-active-learning-literature-survey/) - [Contrastive Estimation: Training Log-Linear Models on Unlabeled Data](https://md.research.elamur.ai/free/en/papers/smith-2005-contrastive-estimation-training-log-linear/) - [Want To Reduce Labeling Cost? GPT-3 Can Help](https://md.research.elamur.ai/free/en/papers/wang-2021-want-reduce-labeling-cost-gpt/) - [Towards Scalable Speech Act Recognition in Twitter: Tackling Insufficient Training Data](https://md.research.elamur.ai/free/en/papers/zhang-2012-scalable-speech-act-recognition-twitter/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{yarowsky1995unsupervised, title = {{Unsupervised Word Sense Disambiguation Rivaling Supervised Methods}}, author = {Yarowsky, David}, booktitle = {33rd Annual Meeting of the Association for Computational Linguistics}, year = {1995}, doi = {10.3115/981658.981684}, url = {https://doi.org/10.3115/981658.981684} } ``` - [← previous Translation using Minimal Recursion Semantics](https://md.research.elamur.ai/free/en/papers/copestake-1995-translation-minimal-recursion-semantics/) - [next → Using Information Content to Evaluate Semantic Similarity in a Taxonomy](https://md.research.elamur.ai/free/en/papers/resnik-1995-information-content-evaluate-semantic-similarity/) - [↑ back to papers of 1995](https://md.research.elamur.ai/free/en/papers/1995/) ## References 25 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Baum, L.E., "An Inequality and Associated Maximization Technique in Statistical Estimation of Probabilistic Functions of a Markov Process," Inequalities, v 3, pp 1-8, 1972. [find](https://scholar.google.com/scholar?q=Baum%2C+L%2EE%2E%2C+%22An+Inequality+and+Associated+Maximization+Technique+in+Statistical+Estimation+of+Probabilistic+Functions+of+a+Markov+Process%2C%22+Inequalities%2C+v+3%2C+pp+1%2D8%2C+1972%2E) 2. Black, Ezra, "An Experiment in Computational Discrimination of English Word Senses," in IBM Journal of Research and Development, v 232, pp 185-194, 1988. [find](https://scholar.google.com/scholar?q=Black%2C+Ezra%2C+%22An+Experiment+in+Computational+Discrimination+of+English+Word+Senses%2C%22+in+IBM+Journal+of+Research+and+Development%2C+v+232%2C+pp+185%2D194%2C+1988%2E) 3. BriU, Eric, "A Corpus-Based Approach to Language Learning," Ph.D. Thesis, University of Pennsylvania, 1993. [find](https://scholar.google.com/scholar?q=BriU%2C+Eric%2C+%22A+Corpus%2DBased+Approach+to+Language+Learning%2C%22+Ph%2ED%2E+Thesis%2C+University+of+Pennsylvania%2C+1993%2E) 4. Brown, Peter, Stephen Della Pietra, Vincent Della Pietra, and Robert Mercer, "Word Sense Disambiguation using Statistical Methods," Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, pp 264-270, 1991. [find](https://scholar.google.com/scholar?q=Brown%2C+Peter%2C+Stephen+Della+Pietra%2C+Vincent+Della+Pietra%2C+and+Robert+Mercer%2C+%22Word+Sense+Disambiguation+using+Statistical+Methods%2C%22+Proceedings+of+the+29th+Annual+Meeting+of+the+Association+for+Comput) [our card](https://md.research.elamur.ai/free/en/papers/brown-1991-word-sense-disambiguation-statistical-methods/) 5. Bruce, Rebecca and Janyce Wiebe, "Word-Sense Disambiguation Using Decomposable Models," in Proceedings of the 32nd Annual Meeting of the Association for Computational Linguistics, Las Cruces, NM, 1994. [find](https://scholar.google.com/scholar?q=Bruce%2C+Rebecca+and+Janyce+Wiebe%2C+%22Word%2DSense+Disambiguation+Using+Decomposable+Models%2C%22+in+Proceedings+of+the+32nd+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+Las+Cruces%2C+NM%2C+1994) 6. Church, K.W., "A Stochastic Parts Program an Noun Phrase Parser for Unrestricted Text," in Proceeding, IEEE International Conference on Acoustics, Speech and Signal Processing, Glasgow, 1989. [find](https://scholar.google.com/scholar?q=Church%2C+K%2EW%2E%2C+%22A+Stochastic+Parts+Program+an+Noun+Phrase+Parser+for+Unrestricted+Text%2C%22+in+Proceeding%2C+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing%2C+Glasgow%2C+1989%2E) 7. Dagan, Ido and Alon Itai, "Word Sense Disambiguation Using a Second Language Monolingual Corpus", Computational Linguistics, v 20, pp 563-596, 1994. [find](https://scholar.google.com/scholar?q=Dagan%2C+Ido+and+Alon+Itai%2C+%22Word+Sense+Disambiguation+Using+a+Second+Language+Monolingual+Corpus%22%2C+Computational+Linguistics%2C+v+20%2C+pp+563%2D596%2C+1994%2E) 8. Dempster, A.P., Laird, N.M, and Rubin, D.B., "Maximum Likelihood From Incomplete Data via the EM Algorithm," Journal of the Royal Statistical Society, v 39, pp 1-38, 1977. [find](https://scholar.google.com/scholar?q=Dempster%2C+A%2EP%2E%2C+Laird%2C+N%2EM%2C+and+Rubin%2C+D%2EB%2E%2C+%22Maximum+Likelihood+From+Incomplete+Data+via+the+EM+Algorithm%2C%22+Journal+of+the+Royal+Statistical+Society%2C+v+39%2C+pp+1%2D38%2C+1977%2E) 9. Gale, W., K. Church, and D. Yarowsky, "A Method for Disambiguating Word Senses in a Large Corpus," Computers and the Humanities, 26, pp 415-439, 1992. [find](https://scholar.google.com/scholar?q=Gale%2C+W%2E%2C+K%2E+Church%2C+and+D%2E+Yarowsky%2C+%22A+Method+for+Disambiguating+Word+Senses+in+a+Large+Corpus%2C%22+Computers+and+the+Humanities%2C+26%2C+pp+415%2D439%2C+1992%2E) 10. Gale, W., K. Church, and D. Yarowsky. "Discrimination Decisions for 100,000-Dimensional Spaces." In A. Zampoli, N. Calzolari and M. Palmer (eds.), Current Issues in Computational Linguistics: In Honour of Don Walker, Kluwer Academic Publishers, pp. 429-450, 1994. [find](https://scholar.google.com/scholar?q=Gale%2C+W%2E%2C+K%2E+Church%2C+and+D%2E+Yarowsky%2E+%22Discrimination+Decisions+for+100%2C000%2DDimensional+Spaces%2E%22+In+A%2E+Zampoli%2C+N%2E+Calzolari+and+M%2E+Palmer+%28eds%2E%29%2C+Current+Issues+in+Computational+Linguistics%3A+In+Honou) 11. Guthrie, J., L. Guthrie, Y. Wilks and H. Aidinejad, "Subject Dependent Co-occurrence and Word Sense Disambiguation," in Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, pp 146-152, 1991. [find](https://scholar.google.com/scholar?q=Guthrie%2C+J%2E%2C+L%2E+Guthrie%2C+Y%2E+Wilks+and+H%2E+Aidinejad%2C+%22Subject+Dependent+Co%2Doccurrence+and+Word+Sense+Disambiguation%2C%22+in+Proceedings+of+the+29th+Annual+Meeting+of+the+Association+for+Computational+Ling) 12. Hearst, Marti, "Noun Homograph Disambiguation Using Local Context in Large Text Corpora," in Using Corpora, University of Waterloo, Waterloo, Ontario, 1991. [find](https://scholar.google.com/scholar?q=Hearst%2C+Marti%2C+%22Noun+Homograph+Disambiguation+Using+Local+Context+in+Large+Text+Corpora%2C%22+in+Using+Corpora%2C+University+of+Waterloo%2C+Waterloo%2C+Ontario%2C+1991%2E) 13. Leacock, Claudia, Geoffrey Towell and Ellen Voorhees "Corpus-Based Statistical Sense Resolution," in Proceedings, ARPA Human Language Technology Workshop, 1993. [find](https://scholar.google.com/scholar?q=Leacock%2C+Claudia%2C+Geoffrey+Towell+and+Ellen+Voorhees+%22Corpus%2DBased+Statistical+Sense+Resolution%2C%22+in+Proceedings%2C+ARPA+Human+Language+Technology+Workshop%2C+1993%2E) 14. Lehman, Jill Fain, "Toward the Essential Nature of Statistical Knowledge in Sense Resolution", in Proceedings of the Twelfth National Conference on Artificial Intelligence, pp 734-471, 1994. [find](https://scholar.google.com/scholar?q=Lehman%2C+Jill+Fain%2C+%22Toward+the+Essential+Nature+of+Statistical+Knowledge+in+Sense+Resolution%22%2C+in+Proceedings+of+the+Twelfth+National+Conference+on+Artificial+Intelligence%2C+pp+734%2D471%2C+1994%2E) 15. Lesk, Michael, "Automatic Sense Disambiguation: How to tell a Pine Cone from an Ice Cream Cone," Proceeding of the 1986 SIGDOC Conference, Association for Computing Machinery, New York, 1986. [find](https://scholar.google.com/scholar?q=Lesk%2C+Michael%2C+%22Automatic+Sense+Disambiguation%3A+How+to+tell+a+Pine+Cone+from+an+Ice+Cream+Cone%2C%22+Proceeding+of+the+1986+SIGDOC+Conference%2C+Association+for+Computing+Machinery%2C+New+York%2C+1986%2E) 16. Miller, George, "WordNet: An On-Line Lexical Database," International Journal of Lexicography, 3, 4, 1990. [find](https://scholar.google.com/scholar?q=Miller%2C+George%2C+%22WordNet%3A+An+On%2DLine+Lexical+Database%2C%22+International+Journal+of+Lexicography%2C+3%2C+4%2C+1990%2E) 17. Mosteller, Frederick, and David Wallace, Inference and Disputed Authorship: The Federalist, Addison-Wesley, Reading, Massachusetts, 1964. [find](https://scholar.google.com/scholar?q=Mosteller%2C+Frederick%2C+and+David+Wallace%2C+Inference+and+Disputed+Authorship%3A+The+Federalist%2C+Addison%2DWesley%2C+Reading%2C+Massachusetts%2C+1964%2E) 18. Rivest, R. L., "Learning Decision Lists," in Machine Learning, 2, pp 229-246, 1987. [find](https://scholar.google.com/scholar?q=Rivest%2C+R%2E+L%2E%2C+%22Learning+Decision+Lists%2C%22+in+Machine+Learning%2C+2%2C+pp+229%2D246%2C+1987%2E) 19. Schiitze, Hinrich, "Dimensions of Meaning," in Proceedings of Supercomputing '92, 1992. [find](https://scholar.google.com/scholar?q=Schiitze%2C+Hinrich%2C+%22Dimensions+of+Meaning%2C%22+in+Proceedings+of+Supercomputing+%2792%2C+1992%2E) 20. Slator, Brian, "Using Context for Sense Preference," in Text-Based Intelligent Systems: Current Research in Text Analysis, Information Extraction and Retrieval, P.S. Jacobs, ed., GE Research and Development Center, Schenectady, New York, 1990. [find](https://scholar.google.com/scholar?q=Slator%2C+Brian%2C+%22Using+Context+for+Sense+Preference%2C%22+in+Text%2DBased+Intelligent+Systems%3A+Current+Research+in+Text+Analysis%2C+Information+Extraction+and+Retrieval%2C+P%2ES%2E+Jacobs%2C+ed%2E%2C+GE+Research+and+Devel) 21. Veronis, Jean and Nancy Ide, "Word Sense Disambiguation with Very Large Neural Networks Extracted from Machine Readable Dictionaries," in Proceedings, COLING-90, pp 389-394, 1990. [find](https://scholar.google.com/scholar?q=Veronis%2C+Jean+and+Nancy+Ide%2C+%22Word+Sense+Disambiguation+with+Very+Large+Neural+Networks+Extracted+from+Machine+Readable+Dictionaries%2C%22+in+Proceedings%2C+COLING%2D90%2C+pp+389%2D394%2C+1990%2E) 22. Yarowsky, David "Word-Sense Disambiguation Using Statistical Models of Roget's Categories Trained on Large Corpora," in Proceedings, COLING-92, Nantes, France, 1992. [find](https://scholar.google.com/scholar?q=Yarowsky%2C+David+%22Word%2DSense+Disambiguation+Using+Statistical+Models+of+Roget%27s+Categories+Trained+on+Large+Corpora%2C%22+in+Proceedings%2C+COLING%2D92%2C+Nantes%2C+France%2C+1992%2E) [our card](https://md.research.elamur.ai/free/en/papers/yarowsky-1992-word-sense-disambiguation-statistical-models/) 23. Yaxowsky, David, "One Sense Per Collocation," in Proceedings, ARPA Human Language Technology Workshop, Princeton, 1993. [find](https://scholar.google.com/scholar?q=Yaxowsky%2C+David%2C+%22One+Sense+Per+Collocation%2C%22+in+Proceedings%2C+ARPA+Human+Language+Technology+Workshop%2C+Princeton%2C+1993%2E) 24. Yarowsky, David, "Decision Lists for Lexical Ambiguity Resolution: Application to Accent Restoration in Spanish and French," in Proceedings of the 32nd Annual Meeting of the Association .for Computational Linguistics, Las Cruces, NM, 1994. [find](https://scholar.google.com/scholar?q=Yarowsky%2C+David%2C+%22Decision+Lists+for+Lexical+Ambiguity+Resolution%3A+Application+to+Accent+Restoration+in+Spanish+and+French%2C%22+in+Proceedings+of+the+32nd+Annual+Meeting+of+the+Association+%2Efor+Computati) [our card](https://md.research.elamur.ai/free/en/papers/yarowsky-1994-decision-lists-lexical-ambiguity-resolution/) 25. Yarowsky, David. "Homograph Disambiguation in Speech Synthesis." In J. Hirschberg, R. Sproat and J. van Santen (eds.), Progress in Speech Synthesis, Springer-Verlag, to appear. [find](https://scholar.google.com/scholar?q=Yarowsky%2C+David%2E+%22Homograph+Disambiguation+in+Speech+Synthesis%2E%22+In+J%2E+Hirschberg%2C+R%2E+Sproat+and+J%2E+van+Santen+%28eds%2E%29%2C+Progress+in+Speech+Synthesis%2C+Springer%2DVerlag%2C+to+appear%2E)