Browse > Article
http://dx.doi.org/10.3745/KIPSTB.2005.12B.3.365

An analysis of Speech Acts for Korean Using Support Vector Machines  

En Jongmin ((주)하나로 드림)
Lee Songwook (동서대학교 컴퓨터공학과)
Seo Jungyun (서강대학교 컴퓨터학과)
Abstract
We propose a speech act analysis method for Korean dialogue using Support Vector Machines (SVM). We use a lexical form of a word, its part of speech (POS) tags, and bigrams of POS tags as sentence features and the contexts of the previous utterance as context features. We select informative features by Chi square statistics. After training SVM with the selected features, SVM classifiers determine the speech act of each utterance. In experiment, we acquired overall $90.54\%$ of accuracy with dialogue corpus for hotel reservation domain.
Keywords
Speech Act Analysis; Support Vector Machines; Feature Selection; Machine Learning;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Yang, Yiming and Jan O. Pedersen. A comparative study on Feature selection in text categorization. In proceedings of the 14th International conference on Machine Learning, 1997
2 Kyungsun Kim, Jungyun Seo, 'Feature selection in automatic speech act tagging', In Proceedings of the 19 ICCPOL, pp.379-383. 2001
3 V. Vapnik. The nature of statistical learning theory, Springer, New York, 1995
4 Joachims, T. http://svmlight.joachims.org
5 Choi, Won Seug, Jeong-Mi Cho, and Jungyun Seo. Analysis System of Speech Acts and Discourse Structures Using Maximum Entropy Model. In Proceedings of the 37th Annual Meeting of the Association for computational Linguistics, 1999, pp.230-237   DOI
6 이재원, 통계적 화행처리를 이용한 대화체 기계번역에서의 효율적인 대화분석, 박사학위논문, 한국과학기술원, 1999
7 Songwook Lee, Jungyun Seo, 'An analysis of Korean speech act using Hidden Markov Model with decision trees', In Proceedings of the 19 ICCPOL, pp.397-400. 2001
8 Lambert, L. and S. Caberry. A Tripatite Plan-Based Model of Dialogue. In Proceedings of ACL, 1991. pp.47-54   DOI
9 Chu-Carroll, J. and S. Carberry. Response Generation in Collaborative Negotiation. ACL-95, 1995   DOI