English Syntactic Disambiguation Using Parser's Ambiguity Type Information

  • Lee, Jae-Won (School of Computer Science and Information, Sungshin Women's University) ;
  • Kim, Sung-Dong (Department of Computer System Engineering, Hansung University) ;
  • Chae, Jin-Seok (Department of Computer Science and Engineering, University of Incheon) ;
  • Lee, Jong-Woo (Department of Computer Engineering, Kwangwoon University) ;
  • Kim, Do-Hyung (School of Computer Science and Information, Sungshin Women's University)
  • 투고 : 2002.05.16
  • 발행 : 2003.06.30

초록

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.

키워드

참고문헌

  1. SMART LANGUAGE TRANSRATE 홈페이지
  2. Proc. of COLING-94 Coping with Ambiguity in Knowledge-based Natural Language Analysis Baker, K.L.;Franz, A.M.;Jordan, P.W.
  3. American Journal of Computational Linguistics v.7 no.2 Relaxation Theories for Parsing Ill-Formed Input Kwasny, S.;Sondheimer, N.K.
  4. ETRI J. v.24 no.6 Speaker Adaptation Using ICA-Based Feature Transformation Jung, Ho-Young;Park, Man-Soo;Kim, Hoi-Rin;Hahn, Min-Soo
  5. Proc. of the Fourteenth Nat’l Conf. on Artificial Intelligence (AAAI97) Statistical Parsing with a Context-Free Grammar and Word Statistics Charniak, E.
  6. Symbolic, Connectionist, and Statistical Approaches to Learning for Natural Language Processing A Statistical Syntactic Disambiguation Program and What It Learns Erasn, M.;Charniak, E.
  7. Proc. of the 37th Annual Meeting of the Association for Computational Linguistics (ACL'99) Estimators for Stochastic Unification-Based Grammars Johnson, M.;Geman, S.;Canon, S.;Chi, Z.;Riezler, S.
  8. Proc. of the 40th Annual Meeting of the Association for Computational Linguistics Parsing the Wall Street Journal Using a Lexical-Functional Grammar and Discriminative Estimation Techniques Riezler, S.;King, T.;Kaplan, R.;Crouch, R.;Maxwell, J.;Johnson, M.
  9. Proc. of COLING-92 Syntactic Preferences for Robust Parsing with Semantic Preferences Wang, J.
  10. Cognition v.2 Seven Principles of Surface Structure Parsing in Natural Language Kimball, J.
  11. Advances in Commectionistg and Neural Computation Theory v.1 Symbolic Neuro Engineering and Natural Language Processing: A Multievel Research Approach Dyer, M.G.
  12. Cognitive Science v.9 Massive Parallel Parsing: A Strongly Interactive Model of Natural Language Interpretation Waltz, D.L.;Pollack, J.B.
  13. Computational Linguistics v.20 no.4 Training and Scaling Preference Functions for Disambiguation Alshawi, H.;Carter, D.
  14. Generalized Phrase Structure Grammar Gazdar, G.;Klein, E.;Pullum, G.;Sag, I.
  15. Structural Disambiguation of to-infinitives Using Augmented Collocations Shim, K.S.
  16. A Study on Prepositional Phrase Attachment and the Transfer of the Preposition Using Semantic Hierarchy Chun, S.J.
  17. Joint SIGDAT Conf. on Empirical Methods in Natural Language Processing and Very Large Corpora Reducing Parsing Complexity by Intra-Sentence Segmentation Based on Maximum Entropy Model Kim, S.D.
  18. Machine Translation v.16 no.3 Learning-Based Intrasentence Segmentation for Efficient Translation of Long Sentences Kim, S.D.;Zhang, B.T.;Kim, Y.T.