Improving Statistical Parser by Recognition of Chinese Number and Quantifier Prefix in Machine Translation

Abstract:

By studying the Chinese number and quantifier prefix (CNQP) as a special language phenomenon in machine translation, this paper presents a CNQP recognition method, which is rule based and independent of word segmentation. The method expressed CNQPs compositions using Backus-Naur Form (BNF), and took the numeral as the active information and the quantifiers as the boundaries of the CNQPs. To avoid the word segmentation noise, a forward maximum matching method was used for obtaining the compositions of the CNQPs, which can be fed into the statistical parser for the analysis of the Chinese sentences. The experimental results indicate the proposed method as a pre-processing module can effectively improve the parsing results of the statistical parser without retraining on experimental data constructed manually, which can further enhance the translation qualities.

• Periodical: Applied Mechanics and Materials (Volumes 427-429)
• Pages: 1841-1844
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.427-429.1841
• Online since: September 2013
• Authors: Wen Xiong*, Yao Hong Jin, Zhi Ying Liu
• Keywords: Backus-Naur Form, Chinese Number, Machine Translation, Quantifier Prefix, Statistical Parser

References

[1] P. Kishore, R. Salim, W. Todd, and W.J. Zhu: Bleu: a method for automatic evaluation of machine translation, in: Proc. ACL' 02, 2002, pp.311-318.

[2] R. Levy and C.D. Manning: Is it harder to parse Chinese, or the Chinese Treebank? in: Proc. ACL '03, 2003, pp.439-446.

DOI: 10.3115/1075096.1075152

[3] K. Martin: Functional unification grammar: a formalism for machine translation, in: Proc. Coling' 84, 1984, pp.75-78.

[4] P. Brown, J. Cocke, S. Della Pietra, V. Della Pietra, F. Jelinek, R. Mercer, and P. Roossin: A statistical approach to language translation, in: Proc. Coling '88, 1988, pp.71-76.

DOI: 10.3115/991635.991651

[5] C. David: A hierarchical phrase-based model for statistical machine translation, in: Proc. ACL '05, (2005).

[6] W. Chao, C. Michael, and K. Philipp: Chinese syntactic reordering for statistical machine translation, in: Proc. 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 2007, pp.737-745.

[7] X. Fei, M. Michael: Improving a statistical MT system with automatically learned rewrite patterns, in: Proc. the 20th international conference on Computational Linguistics, 2004, pp.508-516.

DOI: 10.3115/1220355.1220428

[8] Y.Q. Zhang, Z. Richard, N. Hermann: Chunk-level reordering of source language sentences with automatically learned rules for statistical machine translation, in: Proc. NAACL-HLT 2007/AMTA Workshop on Syntax and Structure in Statistical Translation, 2007, pp.1-8.

DOI: 10.3115/1626281.1626282

[9] Y. Liu, Q. Liu, S. Lin: Tree-to-string alignment template for statistical machine translation, in: Proc. the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2006, pp.609-616.

DOI: 10.3115/1220175.1220252

[10] D. Klein, and C. D. Manning: Fast exact inference with a factored model for natural language parsing, in: Advances in neural information processing systems 15 (2002), 2003, pp.3-10.

[11] X. Song: Composition and Recognition of Noun Quantifier and verb Quantifier Phrase, Ocean Press, Beijing, 2003 (In Chinese).

[12] L. Zhang, W. Xiong, Y.J. Li, and Y. Liu: Recognize modern Chinese quantifier phrases based on a knowledge-database, in: Proc. ICCC '07, 2007 (In Chinese).