--- title: "One Sense per Collocation — Yarowsky 1993" description: "He tests the idea on binary ambiguities with five kinds of \"sense\": hand-tagged homographs French… 92% precision. 12 references, cited by 64 papers here." authors: ["David Yarowsky"] year: 1993 venue: "Human Language Technology: Proceedings of a Workshop Held at Plainsboro, New Jersey, March 21-24, 1993" source: "https://aclanthology.org/H93-1052/" 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-1993-one-sense-per-collocation/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yarowsky-1993-one-sense-per-collocation/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [1993](https://md.research.elamur.ai/free/en/papers/1993/) / One Sense per Collocation # One Sense per Collocation **Authors:** [David Yarowsky](https://md.research.elamur.ai/free/en/authors/david-yarowsky/) · **Year:** 1993 · **Venue:** Human Language Technology: Proceedings of a Workshop Held at Plainsboro, New Jersey, March 21-24, 1993 · **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/H93-1052/) · [PDF](https://aclanthology.org/H93-1052.pdf) · [OpenAlex](https://openalex.org/W2047620598) **Citations:** 376 citations (OpenAlex, 2026-10-14) · [64](https://md.research.elamur.ai/free/en/papers/yarowsky-1993-one-sense-per-collocation/cited-by/) in our library, of the 140,884 papers whose bibliographies we read ## Summary Yarowsky asks whether the surrounding collocation largely determines which sense an ambiguous word takes. This parallels his earlier finding that a word tends to keep one sense within a discourse. He tests the idea on binary ambiguities with five kinds of "sense": - hand-tagged homographs - French translations taken from the Canadian Hansards - homophones - OCR-confusable word pairs - artificial pseudo-words The data come from a 380 million word collection of newswire, abstracts, encyclopedias, books and smaller corpora. Collocation types include adjacent words, nearby words of a given part of speech, and syntactic pairs such as verb/object. For each type he measures the cross-validated entropy of the sense distribution given the collocation, and how well that type alone classifies new examples. A word shows a single sense per collocation in roughly 90–99% of cases. A decision-list classifier that relies on the strongest available local cue reaches 92% precision. The study shows that very local, position-specific evidence is more reliable than unordered wide-context "bag of words" models, especially for verbs and adjectives. This has consequences for building and checking sense-tagged data. ## Key points - **Data:** a 380M-word corpus drawing on AP Newswire, Wall Street Journal, NSF/DOE abstracts, the Canadian Hansards, the Brown Corpus, ATIS/TIMIT, more than 100 books published by Harper & Row, and two encyclopedias (Grolier's and a medical one). Training and test samples were drawn from separate blocks of the corpus. - **Entropy:** cross-validated estimates correct for unseen counter-examples. A 1/0 count implies the minor sense still appears about 6% of the time. Overall entropy for aid/aide was only 0.09 bits. - **Algorithm:** a decision list (Rivest 1987) ranks evidence by the absolute log-likelihood ratio and answers from the single best matching cue, never combining probabilities. - **Reliability of sparse evidence:** - One unopposed word-to-the-right observation gives over 92% accuracy against a 69% prior, and accuracy is near perfect by 15/0. - The same kind of evidence 30 words away adds only about 3% over chance. - Adjacent function words help modestly, up to 13% above chance for verbs. - **Applications:** - Frequent collocations (above 10–15 occurrences) whose senses are mixed should be flagged as likely tagging errors. - Sense tagging can be sped up by assigning all examples of a frequent collocate to one sense. *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: [🧷 Idioms & multiword expressions](https://md.research.elamur.ai/free/en/topics/multiword-expressions/) ## Institutions - [University of Pennsylvania](https://md.research.elamur.ai/free/en/universities/university-of-pennsylvania/) — University, Philadelphia, United States · 143 works · 56,645 citations ## Cite Cite as: David Yarowsky. 1993. One Sense per Collocation. Human Language Technology: Proceedings of a Workshop Held at Plainsboro, New Jersey, March 21-24, 1993. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{yarowsky1993one, title = {{One Sense per Collocation}}, author = {David Yarowsky}, booktitle = {Human Language Technology: Proceedings of a Workshop Held at Plainsboro, New Jersey, March 21-24, 1993}, year = {1993}, doi = {10.3115/1075671.1075731}, url = {https://doi.org/10.3115/1075671.1075731} } ``` - [← previous Retrieving Collocations from Text: Xtract](https://md.research.elamur.ai/free/en/papers/smadja-1993-retrieving-collocations-text-xtract/) - [next → Text-Translation Alignment](https://md.research.elamur.ai/free/en/papers/kay-1993-text-translation-alignment/) - [↑ back to papers of 1993](https://md.research.elamur.ai/free/en/papers/1993/) ## References 12 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Bahl, L., P. Brown, P. de Souza, R. Mercer, "A Tree-Based Statistical Language Model for Natural Language Speech Recognition," in IEEE Transactions on Acoustics, Speech, and Signal Processing, 37, 1989. [find](https://scholar.google.com/scholar?q=Bahl%2C+L%2E%2C+P%2E+Brown%2C+P%2E+de+Souza%2C+R%2E+Mercer%2C+%22A+Tree%2DBased+Statistical+Language+Model+for+Natural+Language+Speech+Recognition%2C%22+in+IEEE+Transactions+on+Acoustics%2C+Speech%2C+and+Signal+Processing%2C+37%2C+198) 2. 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, 1991, pp 264-270. [our card](https://md.research.elamur.ai/free/en/papers/brown-1991-word-sense-disambiguation-statistical-methods/) 3. Gale, W., K. Church, and D. Yarowsky, "One Sense Per Discourse," Proceedings of the 4th DARPA Speech and Natural Language Workshop, 1992. [find](https://scholar.google.com/scholar?q=Gale%2C+W%2E%2C+K%2E+Church%2C+and+D%2E+Yarowsky%2C+%22One+Sense+Per+Discourse%2C%22+Proceedings+of+the+4th+DARPA+Speech+and+Natural+Language+Workshop%2C+1992%2E) 4. Gale, W., K. Church, and D. Yarowsky, "On Evaluation of Word-Sense Disambiguation Systems," in Proceedings, 30th Annual Meeting of the Association for Computational Linguistics, 1992b. [find](https://scholar.google.com/scholar?q=Gale%2C+W%2E%2C+K%2E+Church%2C+and+D%2E+Yarowsky%2C+%22On+Evaluation+of+Word%2DSense+Disambiguation+Systems%2C%22+in+Proceedings%2C+30th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+1992b%2E) 5. Gale, W., K. Church, and D. Yarowsky, "A Method for Disambiguating Word Senses in a Large Corpus," in Computers and the Humanities, 1993. [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+in+Computers+and+the+Humanities%2C+1993%2E) 6. 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) 7. 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) 8. Kelly, Edward, and Phillip Stone, Computer Recognition of English Word Senses, North-Holland, Amsterdam, 1975. [find](https://scholar.google.com/scholar?q=Kelly%2C+Edward%2C+and+Phillip+Stone%2C+Computer+Recognition+of+English+Word+Senses%2C+North%2DHolland%2C+Amsterdam%2C+1975%2E) 9. Resnik, Philip, "A Class-based Approach to Lexical Discovery," in Proceedings of 3Oth Annual Meeting of the Association for Computational Linguistics, 1992. [find](https://scholar.google.com/scholar?q=Resnik%2C+Philip%2C+%22A+Class%2Dbased+Approach+to+Lexical+Discovery%2C%22+in+Proceedings+of+3Oth+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+1992%2E) 10. Rivest, R. L., "Learning Decision Lists," in Machine Learning, 2, 1987, pp 229-246. [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+1987%2C+pp+229%2D246%2E) 11. Sproat, R., J. Hirschberg and D. Yarowsky "A Corpus-based Synthesizer," in Proceedings, International Conference on Spoken Language Processing, Banff, Alberta. October 1992. [find](https://scholar.google.com/scholar?q=Sproat%2C+R%2E%2C+J%2E+Hirschberg+and+D%2E+Yarowsky+%22A+Corpus%2Dbased+Synthesizer%2C%22+in+Proceedings%2C+International+Conference+on+Spoken+Language+Processing%2C+Banff%2C+Alberta%2E+October+1992%2E) 12. Yarowsky, David "Word-Sense Disambiguation Using Statistical Models of Roget's Categories Trained on Large Corpora," in Proceedings, COLING-92, Nantes, France, 1992. [our card](https://md.research.elamur.ai/free/en/papers/yarowsky-1992-word-sense-disambiguation-statistical-models/)