Definition and Extraction of Causal Relations for Question-Answering on Fault-Diagnosis of Electronic Devices

전자장비 고장진단 질의응답을 위한 인과관계 정의 및 추출

  • 이신목 (한국과학기술원 전산학과) ;
  • 신지애 (한국정보통신대학교 공학부)
  • Published : 2008.05.15

Abstract

Causal relations in ontology should be defined based on the inference types necessary to solve problems specific to application as well as domain. In this paper, we present a model to define and extract causal relations for application ontology for Question-Answering (QA) on fault-diagnosis of electronic devices. Causal categories are defined by analyzing generic patterns of QA application; the relations between concepts in the corpus belonging to the causal categories are defined as causal relations. Instances of casual relations are extracted using lexical patterns in the concept definitions of domain, and extended incrementally with information from thesaurus. On the evaluation by domain specialists, our model shows precision of 92.3% in classification of relations and precision of 80.7% in identifying causal relations at the extraction phase.

온톨로지의 인과관계는 특정 응용을 위한 추론에서 중요한 역할을 하므로, 인과관계는 응용에서 쓰이는 추론의 형태에 근거하여 정의되어야 한다. 본 논문에서는, 전자장비의 고장진단 질의응답을 위한 온톨로지에서의 인과관계를 정의하고 추출하는 모델을 제시한다. 질의응답의 패턴을 분석하여 인과범주를 정의하고, 질의응답에서 나타나는 개념들 사이의 관계들 중 인과범주에 속하는 경우를 인과관계로 정의한다. 인과관계 인스턴스는 응용분야의 정의문으로부터 어휘 패턴을 이용하여 추출되고 시소러스 정보를 이용하여 점진적으로 확장된다. 분야 전문가들의 평가 결과, 본 모델은 관계분류에 있어서 92.3%의 평균 정확률과 추출 단계의 인과관계 인식에 있어서 80.7%의 정확률을 보인다.

Keywords

References

  1. Merriam-Webster Online Dictionary. http://www. m-w.com. 2005
  2. 윤평현, 국어의 접속어미 연구. 한신문화사. 1989
  3. D. Chang and K. Choi, Incremental cue phrase learning and bootstrapping method for causality extraction using cue phrase and word pair probabilities, Information Processing & Management, Volume 42, Issue 3, Pages 662-678, 2006 https://doi.org/10.1016/j.ipm.2005.04.004
  4. R. Girju, Automatic Detection of Causal Relations for Question Answering, In Proceedings of the 41st ACL, Workshop on Multilingual Summarization and Question Answering, 2003
  5. R. Girju and D. Moldovan. Mining Answers for Causation Questions, AAAI Symposium on Mining Answers from Texts and Knowledge Bases. 2002
  6. 이신목, 김현수, 황금하, 최기선, "한국어 특허문서상에서의 인과관계 관찰 및 추출," 2006년도 한국인지과학회 춘계학술대회, 2006
  7. C. S. G. Khoo, J. Kornfilt, R. N. Oddy, and S. H. Myaeng. Automatic Extraction of Cause-Effect Information from Newspaper Text without Knowledge-based Inferencing. Literary and Linguistic Computing. Volume 13, Number 4, pp. 177-186. 1998 https://doi.org/10.1093/llc/13.4.177
  8. Y. Kitamura and R. Mizoguchi, Functional Ontology for Functional Understanding, Twelfth International Workshop on Qualitative Reasoning, pp. 77-87, 1998
  9. P. Pantel and M. Pennacchiotti, Espresso: Leveraging Generic Patterns for Automatically Harvesting Semantic Relations, joint conference of the International Committee on Computational Linguistics and the Association for Computational Linguistics, 2006
  10. V. Nastase and S. Szpakowicz. Exploring Noun- modifier Semantic Relations. In Fifth International Workshop on Computational Semantics(IWCS-5), pages 285-301, Tilburg, the Netherlands. 2003
  11. J. Kim, Causes and Events: Mackie on Causation, Journal of Philosophy, Vol. 68, 1971, pp. 426-41. Reprinted in E. Sosa, ed., Causation and Conditionals, Oxford University Press, 1975 https://doi.org/10.2307/2025175
  12. R. Mizoguchi, オントロジー工学, 人工知能学會 編集. オーム社. 2005
  13. J. F. Sowa, Processes and Causality. Available at:http://www.jfsowa.com/ontology/causal.htm. 2002
  14. N. Guarino, Formal Ontology and Information Systems. In. Proceedings of the First International Conference on Formal Ontologies in. Information Systems (FOIS), pp. 3-15. 1998