The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Determining the Dependency among Clauses based on SVM

SVM을 이용한 절-절 간의 의존관계 설정

  • 김미영 (성신여자대학교 컴퓨터정보학부)
  • Published : 2007.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The longer the input sentences, the worse the syntactic parsing results, Therefore, a long sentence is first divided into several clauses and syntactic analysis for each clause is performed. Finally, all the analysis results art merged into one, In the merging process, it is difficult to determine the dependency among clauses, To handle such syntactic ambiguity among clauses, this paper proposes an SVM-based clause-dependency determination method. We extract various features from clauses, and analyze the effect of each feature on the performance. We also compare the performance of our proposed method with those of previous methods.

문장이 길어질수록 구문분석의 정확률이 급격히 떨어지므로, 문장을 분할하여 각각의 분할단위로 구문분석을 수행한 후 각 구문분석결과를 합쳐 완성된 구문트리를 만드는 것이 일반적이다. 이 때 주로 절 단위로 문장이 분할되고, 각 절의 구문분석결과를 통합하게 되는데, 통합 과정에서 절-절 간의 의존관계 설정에 많은 오류가 생긴다. 이러한 절 간의 의존관계의 애매성을 해결하기 위하여, 본 논문은 기계학습을 이용하여 절-절 간의 의존관계를 분석해 본다. Support Vector Machines(SVM)을 사용하여 성능을 평가하고, 본 논문에서 실험한 방법과 기존의 방법들의 성능을 비교해 본 결과, 절-절 간의 의존관계 설정에 있어서 $8.88{\sim}15.35%$의 성능향상을 보였다.

Keywords

References

  1. X. Carreras, L. Marquez, V. Punykanok, adn D. Roth, 'Learning and inference for clause identification', Proc. 13th European Conference on Machine Learning, Helsinki, Finland, pp.35-47, 2002
  2. V. J. Leffa, 'Clause processing in complex sentences', Proc. 1st International Conference on Language Resources and Evaluation, Granada, Spain, 1998
  3. A. Molina and F. Pla, 'Clause detection using HMM', Proc. 5th Conference on Computational Natural Language Learning, Toulouse, France, pp.162-164, 2001
  4. E. F. T. K. Sang and H. Dejean, 'Introduction to the CoNLL-2001 shared task: clause identification', Proc. CoNLL-2001, Toulouse, France, pp. 53-57, 2001
  5. X. Carreras and L. Marquez, 'Boosting Trees for Clause Splitting', Proc. CoNLL-2001, Toulouse, France, pp.73-75, 2001 https://doi.org/10.3115/1117822.1117839
  6. S. Shirai, S. Ikehara, A. Yokoo, and J. Kimura, 'A new dependency analysis method based semantically embedded sentence structures and its performance on Japanese sub ordinate clauses,' Transactions of Information Processing Society of Japan, 36(10):2353-2361, 1995
  7. D. Kawahara and S. Kurohashi, Corpus-based Dependency Analysis of Japanese Sentences using Verb Bunsetsu Transitivity, In Proceedings of the 5th Natural Language Processing Pacific Rim Symposium, pp. 387-391, 1999
  8. F. Minami, 'Gendai Nihongo no Kouzou'(structures of Modern Japanese Language), Taishuukan shoten, 1974
  9. 노마 히데키, '한국어 어휘와 문법의 상관구조', 태학사, 2002
  10. L. Danlos, 'Sentences with two subordinate clauses : syntax, semantics and underspecified semantic representation', In Proceedings of the TAG+7 Workshop, p.140-147, 2004
  11. Yoon-Hyung Roh, Young-Ae Seo, Ki-Young Lee, Sung-Kwon Choi: Long Sentence Partitioning using Structure Analysis for Machine Translation. Proceeding on NLPRS, p.646-652, 2001
  12. T. Utsuro, S. Nishiokayama, M. Fujio, and Y. Matsumoto, 'Analyzing dependencies of Japanese subordinate clauses based on statistics of scope embedding preference,' Proc. 1st Conference of the North, American Chapter of the ACL, pp.110-117, 2000
  13. T. Kudo and Y. Mastumoto, 'Chunking with Support Vector Machines', Proc, 2nd meeting of North American Chapter of Association for Computational Linguistics (NAACL), Pittsburgh, PA, USA, pp.192-199, 2001 https://doi.org/10.3115/1073336.1073361
  14. T. Kudo and Y. Matsumoto, 'Japanese Dependency Structure Analysis Based on Support Vector Machines', Proc. 2000 SIDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora (EMNLP/VLC-2000). Hongkong, China, pp.18-25, 2000
  15. H. Yamada and Y. Matsumoto, 'Statistical Dependency Analysis with Support Vector Machines', Proc. 8th International Workshop on Parsing Technology, Nancy, France, pp.195-206, 2003
  16. Chih- Chung Chang and Chih Jen Lin, LIBSVM: a library for support vector machines, 2001, Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
  17. V. J. Leffa, 'Clause processing in complex sentences', Proc, 1st International Conference on Language Resources and Evaluation, Granada, Spain, 1998