Journal of KIISE:Computing Practices and Letters (한국정보과학회논문지:컴퓨팅의 실제 및 레터)

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

Context Management of Conversational Agent using Two-Stage Bayesian Network

2단계 베이지안 네트워크를 이용한 대화형 에이전트의 문맥 관리

  • 홍진혁 (연세대학교 컴퓨터과학과) ;
  • 조성배 (연세대학교 컴퓨터산업공학부)
  • Published : 2004.02.01
Download PDF
⟨ Previous Next ⟩

Abstract

Conversational agent is a system that provides users with proper information and maintains the context of dialogue on the natural language. Analyzing and modeling process of user's query is essential to make it more realistic, for which Bayesian network is a promising technique. When experts design the network for a domain, the network is usually very complicated and is hard to be understood. The separation of variables in the domain reduces the size of networks and makes it easy to design the conversational agent. Composing Bayesian network as two stages, we aim to design conversational agent easily and analyze user's query in detail. Also, previous information of dialogue makes it possible to maintain the context of conversation. Actually implementing it for a guide of web pages, we can confirm the usefulness of the proposed architecture for conversational agent.

대화형 에이전트는 언어를 이용하여 사용자에게 적절한 정보를 제공하고 대화의 문맥을 유지하는 시스템이다. 대화형 에이전트를 더욱 현실적으로 만들기 위해서는 사용자 질의에 대한 분석과 모델링 과정이 필수적이며, 베이지안 네트워크가 이를 위한 대표적인 방법 중 하나이다. 보통 대상영역을 위한 네트워크는 매우 복잡하고 이해하기가 어렵기 때문에 네트워크를 구성하는 변수들을 분리함으로써 대화형 에이전트를 보다 쉽게 설계할 수 있다. 본 논문에서는 대화형 에이전트의 질의 분석모듈을 2단계 베이지안 네트워크로 구성하여, 설계를 보다 용이하게 하였고 문형을 고려한 세부적인 질의분석을 가능하도록 하였다. 웹 페이지를 소개하는 에이전트에 적용하여 제안한 대화형 에이전트 구조의 유용성을 보였다.

Keywords

References

  1. Y. Yang, L. Chien and L. Lee, 'Speaker intention modeling for large vocabulary mandarin spoken dialogues,' Proceedings of the 4th Int. Conf. on Spoken Language, pp.713-716, 1996 https://doi.org/10.1109/ICSLP.1996.607461
  2. J. Allen, D. Byron, M. Dzikovska, G. Ferguson, L. Galescu and A. Stent, 'Towards conversational human-computer interaction,' AI Magazine, 22(4), pp.27-37, 2001
  3. J. Chai, V. Horvath, N. Nicolov, M. Budzikowska, N. Kambhatla, and W. Zadrozny, 'Natural language sales assistant-A web-based dialog system for online sales,' Proceedings of the 13th Annual Conf. on Innovative Applications of Artificial Intelligence, pp.19-26, 2001
  4. E. Horvitz, J. Breese, D. Heckeman, D. Hovel and K. Rommelse, 'The lumiere project: Bayesian user modeling for inferring the goals and needs of software users,' Proceedings of the 14th Conf. on Uncertainty in Artificial Intelligence, pp.256-265, 1998
  5. D. Albrecht, I. Zukerman, A. Nicholcon and A. Bud, 'Towards a Bayesian model for keyhole plan recognition in large domains,' Proceedings of the 6th Int. Conf. on User Modeling, pp.365-376, 1997
  6. S.I. Lee and S.B. Cho, 'An intelligent agent with structured pattern matching for a virtual representative,' Proceedings of Asia-Pacific Conf. on Intelligent Agent Technology, pp.409-411, 2001
  7. S. Macskassy and S. Stevenson, 'A conversational agent,' Master Essay, Rutgers University, 1996
  8. D. Heckerman and E. Horvitz, 'Inferring informational goals from free-text queries: A Bayesian approach,' Proceedings of the 14th Conf. on Uncertainty in Artificial Intelligence, pp.230-237, 1998
  9. G. Ferguson, J. Allen and B. Miller, 'TRAINS-95: Towards a mixed-initiative planning assistant,' Proceedings of the 3rd Conf. on Artificial Intelligence Planning Systems, pp.70-77, 1996
  10. T. Paek and E. Horvitz, 'Conversation as action under uncertainty,' Proceedings of the 16th Conf. on Uncertainty in Artificial Intelligence, pp.455-464, 2000
  11. E. Charniak, 'Bayesian networks without tears,' AIMagazine, 12(4), pp.50-63, 1991
  12. T. Stephenson, 'An introduction to Bayesian network theory and usage,' IDIAP-RR00-03, 2000
  13. E. Horvitz and T. Paek, 'A computational architecture for conversation,' Proceedings of the 7th Int. Conf. on User Modeling, pp. 201-210, 1999
  14. J. Allen, G. Ferguson and A. Stent, 'An architecture for more realistic conversational systems,' Proceedings of Intelligent User Interfaces, pp.1-8, 2001 https://doi.org/10.1145/359784.359822
  15. J. Allen, 'Mixed initiative interaction,' Proceedings of IEEE Intelligent Systems, pp.14-23, 1999 https://doi.org/10.1109/5254.796083
  16. X. Wu, F.Zheng and M. Xu, 'TOPIC Forest: A plan-based dialog management structure,' Int. Conf. on Acoustics, Speech and Signal Processing, pp.617-620, 2001 https://doi.org/10.1109/ICASSP.2001.940907
  17. B. Grosz and C. Sidner, 'Attention, intention, and the structure of discourse,' Computational Linguistics, 12(3), pp.175-204, 1986