English Syntactic Disambiguation Using Parser's Ambiguity Type Information

ETRI Journal

关键词: parser;    natural language;    grammar tuning;    syntactic preference;    ambiguity type;    Ambiguity resolution;   

Others  :  1184791
DOI  :  10.4218/etrij.03.0102.0401

【 摘 要 】

This paper describes a rule-based approach for syntactic disambiguation used by the English sentence parser in E-TRAN 2001, an English-Korean machine translation system. We propose Parser’s Ambiguity Type Information (PATI) to automatically identify the types of ambiguities observed in competing candidate trees produced by the parser and synthesize the types into a formal representation. PATI provides an efficient way of encoding knowledge into grammar rules and calculating rule preference scores from a relatively small training corpus. In the overall scoring scheme for sorting the candidate trees, the rule preference scores are combined with other preference functions that are based on statistical information. We compare the enhanced grammar with the initial one in terms of the amount of ambiguity. The experimental results show that the rule preference scores could significantly increase the accuracy of ambiguity resolution.

   

【 参考文献 】

• [1]http://www.easytran.com.
• [2]K.L. Baker, A.M. Franz, and P.W. Jordan, "Coping with Ambiguity in Knowledge-based Natural Language Analysis,"Proc. of COLING-94, 1994, pp. 90-94.
• [3]S. Kwasny and N.K. Sondheimer, "Relaxation Theories for Parsing Ill-Formed Input," American Journal of Computational Linguistics, vol. 7, no. 2, 1981, pp. 99-108.
• [4]Ho-Young Jung, Mansoo Park, Hoi-Rin Kim, and Minsoo Hahn, "Speaker Adaptation Using ICA-Based Feature Transformation," ETRI J., vol. 24, no. 6, Dec. 2002, pp. 469-472.
• [5]E. Charniak, "Statistical Parsing with a Context-Free Grammar and Word Statistics," Proc. of the Fourteenth Nat’l Conf. on Artificial Intelligence (AAAI97), 1997, pp. 598-603.
• [6]M. Erasn and E. Charniak, "A Statistical Syntactic Disambiguation Program and What It Learns," Symbolic, Connectionist, and Statistical Approaches to Learning for Natural Language Processing, 1996, pp. 146-159.
• [7]M. Johnson, S. Geman, S. Canon, Z. Chi, and S. Riezler, "Estimators for Stochastic Unification-Based Grammars," Proc. of the 37th Annual Meeting of the Association for Computational Linguistics (ACL’99), 1999.
• [8]S. Riezler, T. King, R. Kaplan, R. Crouch, J. Maxwell, and M. Johnson, "Parsing the Wall Street Journal Using a Lexical-Functional Grammar and Discriminative Estimation Techniques," Proc. of the 40th Annual Meeting of the Association for Computational Lin
• [9]J. Wang, "Syntactic Preferences for Robust Parsing with Semantic Preferences," Proc. of COLING-92, 1992, pp. 239-245.
• [10]J. Kimball, "Seven Principles of Surface Structure Parsing in Natural Language," Cognition, vol. 2, 1973, pp. 15-47.
• [11]M.G. Dyer, "Symbolic Neuro Engineering and Natural Language Processing: A Multilevel Research Approach," Advances in Connectionist and Neural Computation Theory, vol. 1, Ablex Publishing Corp., 1991, pp. 32-68.
• [12]D.L. Waltz and J.B. Pollack, "Massive Parallel Parsing: A Strongly Interactive Model of Natural Language Interpretation," Cognitive Science, vol. 9, 1985, pp. 51-74.
• [13]H. Alshawi and D. Carter, "Training and Scaling Preference Functions for Disambiguation," Computational Linguistics, vol. 20, no. 4, 1994, pp. 635-648.
• [14]G. Gazdar, E. Klein, G. Pullum, and I. Sag, Generalized Phrase Structure Grammar, Blackwell, 1985.
• [15]K.S. Shim, Structural Disambiguation of to-infinitives Using Augmented Collocations, Ph.D. thesis, Department of Computer Engineering, Seoul National University, 1994.
• [16]S.J. Chun, A Study on Prepositional Phrase Attachment and the Transfer of the Preposition Using Semantic Hierarchy, Master thesis, Department of Computer Engineering, Seoul National University, 1994.
• [17]S.D. Kim, "Reducing Parsing Complexity by Intra-Sentence Segmentation Based on Maximum Entropy Model," Joint SIGDAT Conf. on Empirical Methods in Natural Language Processing and Very Large Corpora, 2000.
• [18]S.D. Kim, B.T. Zhang, and Y.T. Kim, "Learning-Based Intrasentence Segmentation for Efficient Translation of Long Sentences," Machine Translation, vol. 16. no. 3, 2001, pp. 151-174.