Article

Free access

One sense per collocation and genre/topic variations

Authors:

David Martinez,

Eneko AgirreAuthors Info & Claims

EMNLP '00: Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora: held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics - Volume 13

Pages 207 - 215

https://doi.org/10.3115/1117794.1117820

Published: 07 October 2000 Publication History

Abstract

This paper revisits the one sense per collocation hypothesis using fine-grained sense distinctions and two different corpora. We show that the hypothesis is weaker for fine-grained sense distinctions (70% vs. 99% reported earlier on 2-way ambiguities). We also show that one sense per collocation does hold across corpora, but that collocations vary from one corpus to the other, following genre and topic variations. This explains the low results when performing word sense disambiguation across corpora. In fact, we demonstrate that when two independent corpora share a related genre/topic, the word sense disambiguation results would be better. Future work on word sense disambiguation will have to take into account genre and topic as important parameters on their models.

References

[1]

Agirre, E. and D. Martinez. Exploring automatic word sense disambiguation with decision lists and the Web. Proceedings of the COLING Workshop on Semantic Annotation and Intelligent Content. Saarbrücken, Germany. 2000.

Digital Library

[2]

Brants, T. TnT-A Statistical Part-of-Speech Tagger. In Proceedings of the Sixth Applied Natural Language Processing Conference, Seattle, WA. 2000.

Digital Library

[3]

Escudero, G., L. Màrquez and G. Rigau. On the Portability and Tuning of Supervised Word Sense Disambiguation Systems. In Proceedings of the Joint Sigdat Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, Hong Kong. 2000.

Digital Library

[4]

Francis, W. M. and H. Kucera. Brown Corpus Manual of Information. Department of Linguistics, Brown University. Also available at http://khnt.hit.uib.no/icame/manuals/brown/. 1964.

[5]

Gale, W., K. W. Church, and D. Yarowsky. A Method for Disambiguating Word Senses in a Large Corpus, Computers and the Humanities, 26, 415--439, 1993.

[6]

Ide, N. and J. Veronis. Introduction to the Special Issue on Word Sense Disambiguation: The State of the Art. Computational Linguistics, 24(1), 1--40, 1998.

Digital Library

[7]

Karlgren, J. and D. Cutting. Recognizing Text Genres with Simple Metrics Using Discriminant Analysis. Proceedings of the International Conference on Computational Linguistics. 1994

Digital Library

[8]

Krovetz, R. More Than One Sense Per Discourse, Proceedings of SENSEVAL and the Lexicography Loop Workshop, http://www.itri.brighton.ac.uk/events/senseval/PROCEEDINGS/. 1998

[9]

Leacock, C., M. Chodorow, and G. A. Miller. Using Corpus Statistics and WordNet Relations for Sense Identification. Computational Linguistics, 24(1), 147--166, 1998.

Digital Library

[10]

Miller, G. A., R. Beckwith, C. Fellbaum, D. Gross, and K. Miller. Five Papers on WordNet. Special Issue of International Journal of Lexicography, 3(4), 1990.

[11]

Miller, G. A., C. Leacock, R. Tengi, and R. T. Bunker, A Semantic Concordance. Proceedings of the ARPA Workshop on Human Language Technology, 1993.

Digital Library

[12]

Ng, H. T. and H. B. Lee. Integrating Multiple Knowledge Sources to Disambiguate Word Sense: An Exemplar-based Approach. Proceedings of the 34th Annual Meeting of the Association for Computational Linguistics. 1996.

Digital Library

[13]

Ng, H. T., C. Y. Lim and S. K. Foo. A Case Study on Inter-Annotator Agreement for Word Sense Disambiguation. Proceedings of the Siglex-ACL Workshop on Standarizing Lexical Resources. 1999.

[14]

Yarowsky, D. One Sense per Collocation. Proc. of the 5th DARPA Speech and Natural Language Workshop. 1993

Digital Library

[15]

Yarowsky, D. Decision Lists for Lexical Ambiguity Resolution: Application to Accent Restoration in Spanish and French. Proceedings of the 32nd Annual Meeting of the Association for Computational Linguistics, pp. 88--95. 1994.

Digital Library

[16]

Yarowsky, D. Unsupervised Word Sense Disambiguation Rivaling Supervised Methods. Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics. Cambridge, MA, pp. 189--196, 1995.

Digital Library

[17]

Yarowsky, D. Homograph Disambiguation in Text-to-speech Synthesis. J Hirschburg, R. Sproat and J. Van Santen (eds.) Progress in Speech Synthesis, Springer-Vorlag, pp. 159--175. 1996.

Cited By

Lopez-Arevalo ISosa-Sosa VRojas-Lopez FTello-Leal E(2017)Improving selection of synsets from WordNet for domain-specific word sense disambiguationComputer Speech and Language10.1016/j.csl.2016.06.00341:C(128-145)Online publication date: 1-Jan-2017
https://dl.acm.org/doi/10.1016/j.csl.2016.06.003
Son JPark S(2012)Learning word sense disambiguation in biomedical text with difference between training and test distributionsInternational Journal of Data Mining and Bioinformatics10.1504/IJDMB.2012.0481996:2(216-237)Online publication date: 1-Jul-2012
https://dl.acm.org/doi/10.1504/IJDMB.2012.048199
Agirre Ede Lacalle OFellbaum CMarchetti AToral AVossen PAgirre EMarquez LWicentowski R(2009)SemEval-2010 task 17Proceedings of the Workshop on Semantic Evaluations: Recent Achievements and Future Directions10.5555/1621969.1621991(123-128)Online publication date: 4-Jun-2009
https://dl.acm.org/doi/10.5555/1621969.1621991
Show More Cited By

One sense per collocation and genre/topic variations
1. Computing methodologies
  1. Artificial intelligence
2. Hardware
  1. Power and energy
    1. Power estimation and optimization

Recommendations

One sense per collocation
HLT '93: Proceedings of the workshop on Human Language Technology

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 ...
One Sense per N-gram
WI-IAT '10: Proceedings of the 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 03

This paper presents a novel supposition, One Sense Per N-gram (N>1), which we believe is appropriate for more linguistic phenomena and can serve as a general version instead of the celebrated One Sense Per Collocation supposition, at least in Chinese ...
Knowledge-based word sense disambiguation using topic models
AAAI'18/IAAI'18/EAAI'18: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence

Word Sense Disambiguation is an open problem in Natural Language Processing which is particularly challenging and useful in the unsupervised setting where all the words in any given text need to be disambiguated without using any labeled data. Typically ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image DL Hosted proceedings

EMNLP '00: Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora: held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics - Volume 13

October 2000

233 pages

Conference Chairs:
Hinrich Schiitze
GroupFire Inc
,
Keh-Yih Su
Behavior Design Corporation

Publisher

Association for Computational Linguistics

United States

Publication History

Published: 07 October 2000

Qualifiers

Article

Acceptance Rates

Overall Acceptance Rate 73 of 234 submissions, 31%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

12
Total Citations
View Citations
284
Total Downloads

Downloads (Last 12 months)35
Downloads (Last 6 weeks)8

Reflects downloads up to 16 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Lopez-Arevalo ISosa-Sosa VRojas-Lopez FTello-Leal E(2017)Improving selection of synsets from WordNet for domain-specific word sense disambiguationComputer Speech and Language10.1016/j.csl.2016.06.00341:C(128-145)Online publication date: 1-Jan-2017
https://dl.acm.org/doi/10.1016/j.csl.2016.06.003
Son JPark S(2012)Learning word sense disambiguation in biomedical text with difference between training and test distributionsInternational Journal of Data Mining and Bioinformatics10.1504/IJDMB.2012.0481996:2(216-237)Online publication date: 1-Jul-2012
https://dl.acm.org/doi/10.1504/IJDMB.2012.048199
Agirre Ede Lacalle OFellbaum CMarchetti AToral AVossen PAgirre EMarquez LWicentowski R(2009)SemEval-2010 task 17Proceedings of the Workshop on Semantic Evaluations: Recent Achievements and Future Directions10.5555/1621969.1621991(123-128)Online publication date: 4-Jun-2009
https://dl.acm.org/doi/10.5555/1621969.1621991
Agirre Ede Lacalle OLascarides AGardent CNivre J(2009)Supervised domain adaption for WSDProceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics10.5555/1609067.1609071(42-50)Online publication date: 30-Mar-2009
https://dl.acm.org/doi/10.5555/1609067.1609071
Son JPark SLee DAltman RSong MHuan J(2009)Learning word sense disambiguation in biomedical text with difference between training and test distributionsProceedings of the third international workshop on Data and text mining in bioinformatics10.1145/1651318.1651330(59-66)Online publication date: 6-Nov-2009
https://dl.acm.org/doi/10.1145/1651318.1651330
Son JSong HPark SPark S(2009)Coping with Distribution Change in the Same Domain Using Similarity-Based Instance WeightingProceedings of the 1st Asian Conference on Machine Learning: Advances in Machine Learning10.1007/978-3-642-05224-8_27(354-366)Online publication date: 3-Nov-2009
https://dl.acm.org/doi/10.1007/978-3-642-05224-8_27
Zhong ZNg HChan YLapata MNg H(2008)Word sense disambiguation using OntoNotesProceedings of the Conference on Empirical Methods in Natural Language Processing10.5555/1613715.1613845(1002-1010)Online publication date: 25-Oct-2008
https://dl.acm.org/doi/10.5555/1613715.1613845
Agirre Ede Lacalle OScott DUszkoreit H(2008)On robustness and domain adaptation using SVD for word sense disambiguationProceedings of the 22nd International Conference on Computational Linguistics - Volume 110.5555/1599081.1599084(17-24)Online publication date: 18-Aug-2008
https://dl.acm.org/doi/10.5555/1599081.1599084
Nissim MMarkert KHinrichs ERoth D(2003)Syntactic features and word similarity for supervised metonymy resolutionProceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 110.3115/1075096.1075104(56-63)Online publication date: 7-Jul-2003
https://dl.acm.org/doi/10.3115/1075096.1075104
Rigau GMagnini BAgirre EVossen PCarroll J(2002)MEANINGProceedings of the 2002 COLING workshop: A roadmap for computational linguistics - Volume 1310.3115/1118754.1118758(1-7)Online publication date: 31-Aug-2002
https://dl.acm.org/doi/10.3115/1118754.1118758
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents