Journal of KIISE (정보과학회 논문지)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Effective Korean Speech-act Classification Using the Classification Priority Application and a Post-correction Rules

분류 우선순위 적용과 후보정 규칙을 이용한 효과적인 한국어 화행 분류

  • 송남훈 (동아대학교 컴퓨터공학과) ;
  • 배경만 (동아대학교 컴퓨터공학과) ;
  • 고영중 (동아대학교 컴퓨터공학과)
  • Received : 2015.08.07
  • Accepted : 2015.10.14
  • Published : 2016.01.15
⟨ Previous Next ⟩

Abstract

A speech-act is a behavior intended by users in an utterance. Speech-act classification is important in a dialogue system. The machine learning and rule-based methods have mainly been used for speech-act classification. In this paper, we propose a speech-act classification method based on the combination of support vector machine (SVM) and transformation-based learning (TBL). The user's utterance is first classified by SVM that is preferentially applied to categories with a low utterance rate in training data. Next, when an utterance has negative scores throughout the whole of the categories, the utterance is applied to the correction phase by rules. The results from our method were higher performance over the baseline system long with error-reduction.

화행이란 발화 속에 포함되어 있는 화자에 의해 의도된 언어적 행위이다. 대화 시스템에서 입력된 발화에 적합한 화행을 분류하는 것은 중요하다. 기존의 화행분류에 관한 연구는 규칙기반과 기계학습 기반의 방법을 많이 사용한다. 본 논문에서는 대표적인 기계학습 방법인 지지벡터기계(SVM)와 변환기반 학습(TBL)을 조합한 화행 분류 방법을 제안한다. 이를 위해, 화행별 학습 발화의 수에 기반하여 분류 우선순위를 조정함으로써 지지벡터기계의 분류 편향 문제를 해결하였고, 오답일 확률이 높은 분류 결과에 대해서 변환 기반 학습을 통해 생성된 보정 규칙을 적용함으로써 화행분류 성능을 개선하는 방법을 제안한다. 본 논문에서 화행별 학습 발화 수의 차이를 고려한 분류 우선순위 변화와 후보정 규칙을 이용한 화행분류 방법을 실험을 통해 평가하였으며, 이는 학습 발화 수가 낮은 화행의 우선순위를 고려하지 않은 기존의 화행 분류보다 성능이 향상되었다.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. Kyung-Sun Kim, Jung-Yun Seo, "Decision of the Korean Speech Act using Feature Selection Method," Journal of Korean Institute of Information Scientists and Engineers, Vol. 30, No. 3, pp. 278-284, 2003.
  2. Min-Jeong Kim, Jae-Hyun Park, Sang-Bum Kim, Hae-Chang Rim, Do-Gil Lee, "A Comparative Study on Optimal Feature Identification and Combination for Korean Dialogue Act Classification," Journal of Korean Institute of Information Scientists and Engineers, Vol. 35, No. 11, pp. 681-691, 2008.
  3. Jongmin En, Songwook Lee, Jungyun Seo, "An analysis of Speech Acts for Korean Using Support Vector Machines," The KIPS Transactions : Part B, Vol. 12, No. 3, pp. 365-368, 2005.
  4. Se-Jong Kim, Yong-Hun Lee, Jong-Hyeok Lee, "Korean Speech Act Tagging using Previous Sentence Features and Following Candidate Speech Acts," Journal of Korean Institute of Information Scientists and Engineers, Vol. 35, No. 6, pp. 374-385, 2008.
  5. Sangwoo Kang, Youngjoong Ko, Jungyun Seo, "Hierarchical speech-act classification for discourse analysis," Pattern Recognition Letters, Vol. 34, pp. 1119-1124.
  6. Kyungsun Kim, "Korean Speech Acts Classification System Using Improved Feature Extraction and Weighting Techniques," doctorate thesis, 2005.
  7. Youngjoong Ko, "New Feature Weighting Approaches for Speech-act Classification," Pattern Recognition Letters, Elsevier Science, Vol. 51, pp. 107-111, 2015. https://doi.org/10.1016/j.patrec.2014.08.014
  8. A. Omuya, V. Prabhakaran, O. Rambow, "Improving the Quality of Minority Class Identification in Dialog Act Tagging," Proc NAACL-HLT, pp. 802-807, 2013.
  9. Won-Seug Choi, Jeong-Mi Cho, Jungyun Seo, "Analysis System of Speech Acts and Discourse Structures Using Maximum Entropy Model," Proc. of 37th Annual Meeting of the ACL, pp. 230-237, 1999.
  10. E. Brill, "Transformation-Based Error-Driven Learning and Natural Language Processing: A Case Study in Part-of-Speech Tagging," Proc. of the Computational Linguistics, pp. 543-565, 1995.
  11. Lee, Jae-won, Jungyun Seo, Gilchang Kim, "A dialogue analysis Model with statistical speech act processing for Dialogue Machine Translation," Workshop in conjunction with (E)ACL' 97, pp. 10-15, 1997.
  12. Hyunjung Lee, Jae-Won Lee, Jungyun Seo, "Speech Act Analysis Model of Korean Utterances for Automatic Dialog Translation," Journal of Korean Institute of Information Scientists and Engineers, Vol. 25, No. 10, pp. 1443-1452, 1998.
  13. Won Seug Choi, Jeong-Mi Cho, and Jungyun Seo, "Analysis System of Speech Acts and Discourse Structures Using Maximum Entropy Model," Proc. of the 37th Annual Meeting of the Association for computational Linguistics, pp. 230-237, 1999.
  14. Lee, Songwook, and Jungyun Seo, "Korean Speech Act Analysis Using Decision Tree," Proc. of the Conference on Hangul and Korean Language Information Processing, pp. 377-381, 1999.