Abstract
This paper proposes a new way to improve the performance of dependency parser: subdividing verbs according to their grammatical functions and integrating the information of verb subclasses into lexicalized parsing model. Firstly, the scheme of verb subdivision is described. Secondly, a maximum entropy model is presented to distinguish verb subclasses. Finally, a statistical parser is developed to evaluate the verb subdivision. Experimental results indicate that the use of verb subclasses has a good influence on parsing performance.
Similar content being viewed by others
References
M. Marcus, B. Santorini, M. Marcinkiewicz. Building a large annotated corpus of English: The Penn treebank. Computational Linguistics, 19(1993)2, 313–330.
M. Collins. Head-driven statistical models for natural language parsing. [Ph.D. dissertation], University of Pennsylvania, 1999.
E. Charniak. A maximum-entropy-inspired parser. Proceedings of the First Annual Meeting of the North American Association for Computational Linguistics, Seattle, Washington, 2000, 132–139.
T. Niesler. Category-based statistical language models. [Ph.D. dissertation], University of Cambridge, 1997.
G. Andrew, T. Grenager, C. Manning. Verb sense and subcategorization: Using joint inference to improve performance on complementary tasks. Proceedings of Empirical Methods in Natural Language Processing, Barcelona, Spain, July 2004, 150–157.
G. Roger, L. Geoffrey, S. Geoffrey. The Computational Analysis of English: A Corpus-based Approach. London, Longman Inc., 1987, chapters 1–3.
N. W. Xue, F. Xia, F. D. Chiou, M. Palmer. The Penn Chinese treebank: phrase structure annotation of a large corpus. Natural Language Engineering, 10(2004)4, 1–30.
Q. Zhou, M. S. Sun. Build a Chinese treebank as the test suite for Chinese parsers. Proceedings of the workshop MAL’99 and NLPRS’99, Beijing, China, 1999, 32–36.
S. W. Yu, et al. The Grammatical Knowledge-base of Contemporary Chinese—A Complete Specification. 2nd ed., Beijing, Tsinghua University Press, 2003, chapter 3.
J. Eisner. Three new probabilistic models for dependency parsing: An exploration. Proceedings of the 16th International Conference on Computational Linguistics (COLING-96), Copenhagen, Denmark, August 1996, 340–345.
D. Klein, C. Manning. Accurate unlexicalized parsing. Proceedings of the 41th Association for Computational Linguistics, Sapporo, Japan, July 2003, 423–430.
R. Levy, C. Manning. Is it harder to parse Chinese, or the Chinese treebank? Proceedings of the 42th Association for Computational Linguistics, Sapporo, Japan, July 2003, 439–446.
N. W. Xue, M. Palmer. Automatic semantic role labeling for Chinese verbs. Proceedings of the 19th International Joint Conference on Artificial Intelligence, Edinburgh, Scotland, August 2005, 1160–1165.
A. Berger, S. D. Pietra, V. D. Pietra. A maximum entropy approach to natural language processing. Computational Linguistics, 22(1996)1, 39–71.
A. Ratnaparkhi. A maximum entropy part-of-speech tagger. Proceedings of the First Empirical Methods in Natural Language Processing Conference, Philadelphia, PA, USA, 1996, May, 133–142.
A. Ratnaparkhi. Learning to parse natural language with maximum entropy models. Machine Learning, 34(1999)1–3, 151–175.
J. N. Darroch, D. Ratcliff. Generalized iterative scaling for log-linear models. Annals of Mathematical statistics, 43(1972)5, 1470–1480.
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the National Natural Science Foundation of China (No.60435020, 60575042 and 60503072).
Communication author: Liu Ting, born in 1972, male, Ph.D., professor. Computer Science and Technology School, Harbin Institute of Technology, Harbin 150001, China.
About this article
Cite this article
Liu, T., Ma, J., Zhang, H. et al. Subdividing verbs to improve syntactic parsing. J. of Electron.(China) 24, 347–352 (2007). https://doi.org/10.1007/s11767-005-0193-8
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11767-005-0193-8