The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
One sense per collocation
Abstract
Previous work [Gale, Church and Yarowsky, 1992] showed that with high probability a polysemous word has one sense per discourse. In this paper we show that for certain definitions of collocation, a polysemous word exhibits essentially only one sense per collocation. We test this empirical hypothesis for several definitions of sense and collocation, and discover that it holds with 90--99% accuracy for binary ambiguities. We utilize this property in a disambiguation algorithm that achieves precision of 92% using combined models of very local context.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Rivest, R. L. (1987) · Machine Learning · doi:10.1007/bf00058680 · Cited by 886
Word-sense disambiguation using statistical models of Roget's categories trained on large corpora
Yarowsky, D. (1992) · Proceedings of the 14th conference on Computational linguistics - · doi:10.3115/992133.992140 · Cited by 663
Self-citationA method for disambiguating word senses in a large corpus
Gale, W. A., Church, K., & Yarowsky, D. (1992) · Computers and the Humanities · doi:10.1007/bf00136984 · Cited by 532
Self-citationGale, W. A., Church, K. W., & Yarowsky, D. (1992) · Proceedings of the workshop on Speech and Natural Language - HLT '91 · doi:10.3115/1075527.1075579 · Cited by 522
Self-citationWord-sense disambiguation using statistical methods
Brown, P. F., Pietra, S. A. D., Pietra, V. J. D., & Mercer, R. L. (1991) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.3115/981344.981378 · Cited by 365
A tree-based statistical language model for natural language speech recognition
Bahl, L. R., Brown, P. F., de Souza, P. V., & Mercer, R. L. (1989) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/29.32278 · Cited by 255
Corpus-based statistical sense resolution
Leacock, C., Towell, G. G., & Voorhees, E. M. (1993) · DARPA Workshop on Speech and Natural Language (HLT) · doi:10.3115/1075671.1075730 · Cited by 154
A class-based approach to lexical discovery
Resnik, P. (1992) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.3115/981967.982021 · Cited by 107
A Tree-Based Statistical Language Model for Natural Language Speech Recognition
Bahl, L. R., Brown, P. F., de Souza, P. V., et al. (1990) · Elsevier eBooks · doi:10.1016/b978-0-08-051584-7.50046-2 · Cited by 35
Cited by
Unsupervised word sense disambiguation rivaling supervised methods
Yarowsky, D. (1995) · Proceedings of the 33rd annual meeting on Association for Computational Linguistics - · doi:10.3115/981658.981684 · Cited by 2,385
Self-citationWord sense disambiguation: A survey
Navigli, R. (2009) · ACM Computing Surveys · doi:10.1145/1459352.1459355 · Cited by 1,819
The communicative function of ambiguity in language
Piantadosi, S. T., Tily, H., & Gibson, E. (2012) · Cognition · doi:10.1016/j.cognition.2011.10.004 · Cited by 628
“Nearly all frequent words have multiple senses but word senses can be disambiguated reasonably well by computational models (Navigli, 2009), even using very simple knowledge of context or heuristics (Gale, Church, & Yarowsky, 1992; Yarowsky, 1993).”
Translating Collocations for Bilingual Lexicons: A Statistical Approach
McKeown, K. R., Smadja, F., & Hatzivassiloglou, V. (1996) · doi:10.7916/d8c82m3r · Cited by 490
Hownet and the Computation of Meaning: (With CD-ROM)
Dong, Z., & Dong, Q. (2006) · WORLD SCIENTIFIC eBooks · doi:10.1142/5935 · Cited by 443
Using corpus statistics and WordNet relations for sense identification
Leacock, C., Miller, G. A., & Chodorow, M. S. (1998) · doi:10.5555/972719.972726 · Cited by 439
Yarowsky, D. (1994) · Proceedings of the 32nd annual meeting on Association for Computational Linguistics - · doi:10.3115/981732.981745 · Cited by 356
Self-citationWord sense disambiguation and information retrieval
Sanderson, M. (1994) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.5555/188490.188548 · Cited by 340
Integrating Subject Field Codes into WordNet
Magnini, B., & Cavaglià, G. (2000) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/36otuawjvvk5 · Cited by 328
An Experimental Study of Graph Connectivity for Unsupervised Word Sense Disambiguation
Navigli, R., & Lapata, M. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.36 · Cited by 288
Metadata
- Authors
- Yarowsky, D.
- Venue
- Proceedings of the workshop on Human Language Technology - HLT '93
- Published
- 1993
- Pages
- 266
- OpenAlex
- W2047620598
- Cited by
- 376
- References
- 9
- Type
- conference abstract
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.