Abstract
In parse selection, the task is to select the correct syntactic analysis of a given sentence from a set of parses generated by some other mechanism. On the basis of correctly labeled examples, supervised parse selection techniques can be employed to obtain reasonable accuracy. Although parsing has improved enormously over the last few years, even the most successful parsers make very silly, sometimes embarrassing, mistakes. In our experiments with a large wide-coverage stochastic attribute-value grammar of Dutch, we noted that the system sometimes is insensitive to the naturalness of the various lexical combinations it has to consider. Although parsers often employ lexical features which are in principle able to represent preferences with respect to word combinations, the size of the manually labeled training data will be too small to be able to learn the relevance of such features.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Note that the error reduction numbers presented in the table are lower than those presented in van Noord and Malouf (2005). The reason is that we report here on experiments in which parses are generated with a version of Alpino with the POS-tagger switched on. The POS-tagger already reduces the number of ambiguities, and in particular solves many of the “easy” cases. The resulting models, however, are more effective in practice (where the model also is applied after the POS-tagger).
References
Abekawa, T. and M. Okumura (2006). Japanese dependency parsing using co-occurrence information and a combination of case elements. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Sydney, pp. 833–840.
Boros, M., W. Eckert, F. Gallwitz, G. Görz, G. Hanrieder, and H. Niemann (1996). Towards understanding spontaneous speech: word accuracy vs. concept accuracy. In Proceedings of the 4th International Conference on Spoken Language Processing (ICSLP 96), Philadelphia, PA, pp. 1009–1012.
Bouma, G. and G. Kloosterman (2002). Querying dependency treebanks in XML. In Proceedings of the 3rd International Conference on Language Resources and Evaluation (LREC), Gran Canaria, pp. 1686–1691.
Bouma, G. and G. Kloosterman (2007). Mining syntactically annotated corpora using XQuery. In Proceedings of the Linguistic Annotation Workshop, Proceedings of the Linguistic Annotation Workshop (ACL’07), Prague, pp. 17–24.
Briscoe, T., J. Carroll, J. Graham, and A. Copestake (2002). Relational evaluation schemes. In Proceedings of the Beyond PARSEVAL Workshop at the 3rd International Conference on Language Resources and Evaluation, Las Palmas, Gran Canaria, pp. 4–8.
Church, K.W., W.A. Gale, P. Hanks, and D. Hindle (1989). Parsing, word association and typical predicate argument relations. In Proceedings of the 1st International Workshop on Parsing Technologies (IWPT ’89), Carnegie Mellon University, Pittsburg, PA, pp. 389–398.
Church, K.W. and P. Hanks (1990). Word association norms, mutual information and lexicography. Computational Linguistics 16(1):22–29.
Fano, R.M. (1961). Transmission of Information: A Statistical Theory of Communications. Cambridge, MA: MIT Press.
Gamallo, P., A. Agustini, and G.P. Lopes (2003). Learning subcategorisation information to model a grammar with “co-restrictions”. TAL 44(1):93–117.
Hoekstra, H., M. Moortgat, B. Renmans, M. Schouppe, I. Schuurman, and T. van derWouden (2003). CGN Syntactische Annotatie. CGN Internal Project Report, available at http://www.ccl.kuleuven.be/Papers/sa-man.DEF.pdf
Johnson, M. and S. Riezler (2000). Exploiting auxiliary distributions in stochastic unification-based grammars. In Proceedings of the 1st Conference on North American Chapter of the Association for Computational Linguistics, Morgan Kaufmann Publishers Inc., San Francisco, CA, pp. 154–161.
Kawahara, D. and S. Kurohashi (2006). A fully-lexicalized probabilistic model for Japanese syntactic and case structure analysis. In Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Association for Computational Linguistics, Morristown, NJ, pp. 176–183.
Kawahara, D. and S. Kurohashi (2008). Coordination disambiguation without any similarities. In Proceedings of the 22nd International Conference on Computational Linguistics (COLING 2008), Manchester, pp. 425–432.
Malouf, R. (2002). A comparison of algorithms for maximum entropy parameter estimation. In Proceedings of the 6th Conference on Natural Language Learning (CoNLL-2002), Taipei, pp. 49–55.
McCarthy, D. (2001). Lexical acquisition at the syntax-semantics interface: diathesis alternations, subcategorization frames and selectional preferences. Ph.D. thesis, University of Sussex.
McClosky, D., E. Charniak, and M. Johnson (2006). Effective self-training for parsing. In Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, Association for Computational Linguistics, New York City, NY, pp. 152–159.
Merlo, P. and S. Stevenson (2001). Automatic verb classification based on statistical distributions of argument structure. Computational Linguistics 27(3):373–408.
Ordelman, R., F. de Jong, A. van Hessen, and H. Hondorp (2007). TwNC: a multifaceted Dutch news corpus. ELRA Newsletter 12(3/4):4–7.
Prins, R. (2005). Finite-state pre-processing for natural language analysis. Ph.D. thesis, University of Groningen.
Resnik, P.S. (1993). Selection and information: a class-based approach to lexical relationships. Ph.D. thesis, University of Pennsylvania, Philadelphia, PA.
Ribas, F. (1995). On learning more appropriate selectional restrictions. In Proceedings of the 7th Conference on European Chapter of the Association for Computational Linguistics, Morgan Kaufmann Publishers Inc., San Francisco, CA, pp. 112–118, DOI http://dx.doi.org/10.3115/976973.976990
Schulte im Walde, S. (2009). The induction of verb frames and verb classes from corpora. In A. Lüdeling and M. Kytö (Eds.), Corpus Linguistics. An International Handbook. Berlin: Mouton de Gruyter.
van Noord, G. (2006). At last parsing is now operational. In TALN 2006, Actes de la 13e Conference sur le Traitement Automatique des Langues Naturelles, Leuven, pp. 20–42.
van Noord, G. and R. Malouf (2005). Wide coverage parsing with stochastic attribute value grammars, draft available from http://www.let.rug.nl/~vannoord. A preliminary version of this paper was published in the Proceedings of the IJCNLP Workshop Beyond Shallow Analyses, Hainan, 2004.
van Noord, G., I. Schuurman, and V. Vandeghinste (2006). Syntactic annotation of large corpora in STEVIN. In Proceedings of the 5th International Conference on Language Resources and Evaluation (LREC), Genoa.
Whittemore, G., K. Ferrara, and H. Brunner (1990). Empirical study of predictive powers of simple attachment schemes for post-modifier prepositional phrases. In Proceedings of the 28th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Pittsburgh, PA, pp. 23–30, DOI 10.3115/981823.981827.
Acknowledgements
This research was carried out in part in the context of the Lassy project. The Lassy project is carried out within the STEVIN programme which is funded by the Dutch and Flemish governments http://taalunieversum.org/taal/technologie/stevin.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer Science+Business Media B.V.
About this chapter
Cite this chapter
van Noord, G. (2010). Self-Trained Bilexical Preferences to Improve Disambiguation Accuracy. In: Bunt, H., Merlo, P., Nivre, J. (eds) Trends in Parsing Technology. Text, Speech and Language Technology, vol 43. Springer, Dordrecht. https://doi.org/10.1007/978-90-481-9352-3_11
Download citation
DOI: https://doi.org/10.1007/978-90-481-9352-3_11
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-90-481-9351-6
Online ISBN: 978-90-481-9352-3
eBook Packages: Humanities, Social Sciences and LawSocial Sciences (R0)