Hostname: page-component-8448b6f56d-t5pn6 Total loading time: 0 Render date: 2024-04-24T23:52:35.166Z Has data issue: false hasContentIssue false
  • English
  • Français

Class-based approach to disambiguating Levin verbs

Published online by Cambridge University Press:  11 October 2010

JIANGUO LI  and
CHRIS BREW
JIANGUO LI
Affiliation:
Applied Research Center, Motorola, Schaumburg, IL 60196, USA email: jianguo.li@motorola.com
CHRIS BREW
Affiliation:
Department of Linguistics, Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43201, USA email: cbrew@ling.osu.edu
Get access Rights & Permissions [Opens in a new window]

Abstract

Lapata and Brew (Computational Linguistics, vol. 30, 2004, pp. 295–313) (hereafter LB04) obtain from untagged texts a statistical prior model that is able to generate class preferences for ambiguous Lewin (English Verb Classes and Alternations: A Preliminary Investigation, 1993, University of Chicago Press) verbs (hereafter Levin). They also show that their informative priors, incorporated into a Naive Bayes classifier deduced from hand-tagged data (HTD), can aid in verb class disambiguation. We re-analyse LB04's prior model and show that a single factor (the joint probability of class and frame) determines the predominant class for a particular verb in a particular frame. This means that the prior model cannot be sensitive to fine-grained lexical distinctions between different individual verbs falling in the same class.

We replicate LB04's supervised disambiguation experiments on large-scale data, using deep parsers rather than the shallow parser of LB04. In addition, we introduce a method for training our classifier without using HTD. This relies on knowledge of Levin class memberships to move information from unambiguous to ambiguous instances of each class. We regard this system as unsupervised because it does not rely on human annotation of individual verb instances. Although our unsupervised verb class disambiguator does not match the performance of the ones that make use of HTD, it consistently outperforms the random baseline model. Our experiments also demonstrate that the informative priors derived from untagged texts help improve the performance of the classifier trained on untagged data.

Type
Papers
Information
Natural Language Engineering , Volume 16 , Special Issue 4: Distributional Lexical Semantics , October 2010 , pp. 391 - 415
Copyright
Copyright © Cambridge University Press 2010

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Carroll, G., and Rooth, M. 1998. Valence induction with a head-lexicalized PCFG. In Proceedings of the 1998 Conference on EMNLP, pp. 58–63.Google Scholar
Charniak, E. 2000. A maximum-entropy-inspired parser. In Proceedings of the 2000 Conference of NAACL, pp. 132–139.Google Scholar
Corley, S., Corley, M., Keller, F., Cocker, M., and Trewin, S. 2001. Finding syntactic structure in unparsed corpora. Computers and the Humanities 35 (2): 81–94.CrossRefGoogle Scholar
Dang, H., Kipper, K., Palmer, M., and Rosenzweig, J. 1998. Investigating regular sense extensions based on intersective Levin classes. In Proceedings of the 17th International Conference on COLING and 36th Annual Meeting of ACL, pp. 293–299.Google Scholar
Dowty, D. 1991. Thematic proto-roles and argument selection. Language 67: 547–619.CrossRefGoogle Scholar
Dunning, T. 1993. Accurate methods for the statistics of surprise and coincidence. Computational Linguistics 19 (1): 61–74.Google Scholar
Gildea, D., and Jurafsky, D. 2002. Automatic labeling of semantic role. Computational Linguistics 28 (3): 245–288.CrossRefGoogle Scholar
Goldberg, A. 1995. Constructions. Chicago: University of Chicago Press.Google Scholar
Green, G. 1974. Semantics and Syntactic Regularity. Bloomington: Indiana University Press.Google Scholar
Henderson, J. 2003. Inducing history representations for broad-coverage statistical parsing. In Proceedings of the 2003 Joint Meeting of NAACL/HLT, pp. 103–110.Google Scholar
Hoste, V., Kool, A., and Daelemans, W. 2001. Classifier optimization and combination in the English all words tasks. In Proceedings of the SENSEVAL-2 Workshop, pp. 84–86.Google Scholar
Hoste, V., Hendrickx, I., Daelemans, W., and van den Bosch, A. 2002. Parameter optimization for machine learning of word sense disambiguation. Natural Language Engineering 8 (4): 311–325.CrossRefGoogle Scholar
Joanis, E., Stevenson, S., and James, D. 2007. A general feature space for automatic verb classification. Natural Language Engineering 1: 1–31.Google Scholar
Kipper, K., Dang, H., and Palmer, M. 2000. Class-Based Construction of a Verb Lexicon. In Proceedings of AAAI/IAAI, pp. 691–696.Google Scholar
Korhonen, A. 2002. Subcategorization Acquisition. Cambridge University Press.Google Scholar
Korhonen, A., Krymolowski, Y., and Marx, Z. 2003. Clustering polysemic subcategorization frame distributions semantically. In Proceedings of the 41st Annual Meeting of ACL, pp. 64–71.Google Scholar
Korhonen, A., and Preiss, J. 2003. Improving subcategorization acquisition using word sense disambiguation. In Proceedings of the 41st Annual Meeting of ACL, pp. 48–55.Google Scholar
Lapata, M. 1999. Acquiring lexical generalizations from corpora: a case study for diathesis alternations. In Proceedings of the 37th Annual Meeting of ACL, pp. 397–404.Google Scholar
Lapata, M., and Brew, C. 2004. Verb class disambiguation using informative priors. Computational Linguistics 30 (1): 295–313.CrossRefGoogle Scholar
Leacock, C., Chodorow, C., and Miller, C. 1998. Using corpus statistics and WordNet relations for sense identification. Computational Linguistics 24 (1): 147–165.Google Scholar
Lee, K., and Ng, H. 2002. An empirical evaluation of knowledge sources and learning algorithm for word sense disambiguation. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing, pp. 41–48.Google Scholar
Levin, B. 1993. English Verb Classes and Alternations: A Preliminary Investigation. Chicago: University of Chicago Press.Google Scholar
Li, J., and Brew, C. 2008. Which are the best features for automatic verb classification. In Proceedings of the 46th Annual Meeting of ACL, pp. 434–442.Google Scholar
Lin, D. 1998. Automatic retrieval and clustering of similar words. In Proceedings of the 17th International Conference on COLING and 36th Annual Meeting of ACL, pp. 768–774.Google Scholar
McCarthy, D., Koeling, R., Weeds, J., and Carroll, J. 2004. Finding predominant senses in untagged text. In Proceedings of the 42nd Annual Meeting of ACL, pp. 280–287.Google Scholar
Merlo, P., Joanis, E., and Henderson, J. 2005. Unsupervised verb class disambiguation based on diathesis alternations, Manuscript.Google Scholar
Merlo, P., and Stevenson, S. 2001. Automatic verb classification based on statistical distribution of argument structure. Computational Linguistics 27 (3): 373–408.CrossRefGoogle Scholar
Minnen, G., Carroll, J., and Pearce, D. 2000. Applied morphological processing of English. Natural Language Engineering 7 (3): 207–223.CrossRefGoogle Scholar
Pado, S., and Lapata, M. 2003. Constructing semantic space from parsed corpora. In Proceedings of the 41st Annual Meeting of ACL, pp. 545–552.Google Scholar
Palmer, M. 2000. Consistent criteria for sense distinction. Computers and the Humanities 1 (2): 217–222.CrossRefGoogle Scholar
Rohde, D., Gonnerman, L., and Plaut, D. 2004. An improved method for deriving word meaning from lexical co-occurrence. Cognitive Psychology 7: 573–605.Google Scholar
Schulte im Walde, S. 2000. Clustering verbs semantically according to alternation behavior. In Proceedings of the 18th International Conference on COLING, pp. 747–753.Google Scholar
Schutze, H. 1998. Automatic word sense disambiguation. Computational Linguistics 24 (1): 97–124.Google Scholar
Shen, D., and Lapata, M. 2007. Using semantic roles to improve question answering. In Proceedings of the 2007 Conference on EMNLP-CoNLL, pp. 12–21.Google Scholar
Shi, L., and Mihalcea, R. 2005. Put pieces together: combining FrameNet, VerbNet and WordNet for robust semantic parsing. In Proceedings of the 6th International Conference on Computational Linguistics and Intelligent Text Processing, pp. 100–111.Google Scholar
Swier, R., and Stevenson, S. 2004. Unsupervised semantic role labelling. In Proceedings of the 2004 Conference on EMNLP, pp. 95–102.Google Scholar
Yarowsky, D. 1992. Word-sense disambiguation using statistical models of Roget's categories trained on large corpora. In Proceedings of the 15th International Conference on COLING, pp. 88–94.Google Scholar