Abstract
We investigate the effect of unlexicalization in a dependency parser for variable word order languages and propose an unlexicalized parser which can utilize some contextual information in order to achieve performance comparable to that of lexicalized parsers. Unlexicalization of an early dependency parser makes performance decrease by 3.6%. However, when we modify the unlexicalized parser into the one which can consider additional contextual information, the parser performs better than some lexicalized dependency parsers, while it requires simpler smoothing processes, less time and space for parsing.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Collins, M.: Head-Driven Statistical Models for Natural Language Parsing. PhD thesis, University of Pennsylvania (1999)
Charniak, E.: A maximum-entropy-inspired parser. Technical Report CS-99-12, Department of Computer Science, Brown University (1999)
Charniak, E.: Immediate-head parsing for language models. In: Meeting of the Association for Computational Linguistics, pp. 116–123 (2001)
Gildea, D.: Corpus variation and parser performance. In: Proceedings of Conference on Empirical Methods in Natural Language Processing (2001)
Klein, D., Manning, C.D.: Accurate unlexicalized parsing. In: Proceedings of the 41st Meeting of the Association for Computational Linguistics, pp. 310–315 (2003)
Collins, M.J.: A new statistical parser based on bigram lexical dependencies. In: Proceedings of the 34th Annual Meeting of the ACL (1996)
Lee, K.J.: Probabilistic Parsing of Korean based on Language-Specific Properties. PhD thesis, Dept. of Computer Science. KAIST (1997)
Haruno, M., Shirai, S., Ooyama, Y.: Using decision trees to construct a practical parser. In: Proceedings of COLING-ACL 1998, pp. 505–512 (1998)
Kim, H., Seo, J.: A statistical Korean parser based on lexical dependencies. In: Spring Proceedings of Conference on Korea AI Society (1997)
Uchimoto, K., Sekine, S., Isahara, H.: Japanese dependency structure analysis based on maximum entropy models. In: Proceedings of 13th EACL, pp. 196–203 (1999)
Kanayama, H., Torisawa, K., Mitsuichi, Y., Tsujii, J.: Statistical dependency analysis with an HPSG-based Japanese grammar. In: Proceedings of 5th Natural Language Processing Pacific Rim Symposium, pp. 138–143 (1999)
Kanayama, H., Torisawa, K., Mitsuichi, Y., Tsujii, J.: A hybrid Japanese parser with an hand-crafted grammar and statistics. In: Proceedings of the COLING 2000, pp. 411–417 (2000)
Sekine, S., Uchimoto, K., Isahara, H.: Backward beam search algorithm for dependency analysis of japanese. In: Proceedings of the COLING 2000, pp. 745–760 (2000)
Choi, K.S.: KAIST Language Resources v.2001. Result of Core Software Project from Ministry of Science and Technology, Korea (2001), http://kibs.kaist.ac.kr
Sekine, S.: Japanese dependency analysis using a deterministic definite state transducer. In: Proceedings of the COLING 2000, pp. 761–767 (2000)
Charniak, E.: Tree-bank grammars. Technical Report CS-96-02, Department of Computer Science, Brown University (1996)
Seo, K.J., Nam, K.C., Choi, K.S.: A probabilistic model of the dependency parse for the variable-word-order languages by using ascending dependency. Computer Processing of Oriental Languages 12, 309–322 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chung, H., Rim, HC. (2004). Unlexicalized Dependency Parser for Variable Word Order Languages Based on Local Contextual Pattern. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2004. Lecture Notes in Computer Science, vol 2945. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24630-5_14
Download citation
DOI: https://doi.org/10.1007/978-3-540-24630-5_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21006-1
Online ISBN: 978-3-540-24630-5
eBook Packages: Springer Book Archive