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

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

Train Booking Agent with Adaptive Sentence Generation Using Interactive Genetic Programming

대화형 유전 프로그래밍을 이용한 적응적 문장생성 열차예약 에이전트

  • Published : 2006.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

As dialogue systems are widely required, the research on natural language generation in dialogue has raised attention. Contrary to conventional dialogue systems that reply to the user with a set of predefined answers, a newly developed dialogue system generates them dynamically and trains the answers to support more flexible and customized dialogues with humans. This paper proposes an evolutionary method for generating sentences using interactive genetic programming. Sentence plan trees, which stand for the sentence structures, are adopted as the representation of genetic programming. With interactive evolution process with the user, a set of customized sentence structures is obtained. The proposed method applies to a dialogue-based train booking agent and the usability test demonstrates the usefulness of the proposed method.

대화형 에이전트가 다양한 분야에서 적용됨에 따라서 현실성 있는 대화 생성을 위한 자연언어 생성에 대한 연구가 관심을 끌고 있다. 대화형 에이전트에서는 보통 미리 준비된 답변을 이용하여 사용자와 대화를 수행하지만, 최근에는 문장을 동적으로 생성하고 학습함으로써 보다 유연하고 현실성있는 서비스를 제공하는 대화형 에이전트가 활발히 연구되고 있다. 본 논문에서는 대화형 유전 프로그래밍을 이용한 문장생성 방법을 제안한다. 이 방법은 문장의 구조를 나타내는 문장계획 트리로 인코딩된 개체를 평가자의 평가를 통해 적응적인 문장을 얻는다. 이 방법의 유용성을 검증하기 위해 제안하는 방법으로 열차예약 에이전트를 구현한 후, 사용자 평가를 수행하였다. 그 결과 제안하는 방법이 도메인에 적합한 문장을 생성하는 것을 확인할 수 있었다.

Keywords

References

  1. S. Macskassy and S. Stevenson, 'A conversational agent,' Master Essay, Rutgers university, 1996
  2. V. Zue and J. Class, 'Conversational interfaces: Advances and challenges,' Proc. of the IEEE, vol., 88, no. 8, pp. 1166-1180, 2000 https://doi.org/10.1109/5.880078
  3. M. A. Walker, O. C. Rambow and M. Rogati, 'Training a sentence planner for spoken dialogue using boosting,' Computer Speech and Language, vol. 16, no. 3-4, pp. 409-433, 2002 https://doi.org/10.1016/S0885-2308(02)00027-X
  4. M. Theune, 'Natural language generation for dialogue: System survey,' TR-CTIT-03-22, 2003
  5. A. Ratnaparkhi, 'Trainable approaches to surface natural language generation and their application to conversational dialog systems,' Computer Speech and Language, vol. 16, no. 3-4, pp. 435-455, 2002 https://doi.org/10.1016/S0885-2308(02)00025-6
  6. E. Levin, R. Pieraccini and W. Eckert., 'A stochastic model of human-machine interaction for learning dialog strategies,' IEEE Trans. Speech and Audio Processing, vol. 8, no. 1, pp. 11-23, 2000 https://doi.org/10.1109/89.817450
  7. I. Bulyko and M. Ostendorf, 'Efficient integrated response generation from multiple targets using weighted finite state transducers,' Computer Speech and Language, vol. 16, no. 3-4, pp. 533-550, 2002 https://doi.org/10.1016/S0885-2308(02)00023-2
  8. W. Wei wei, L. Biqi, C. Fang and Y. Baozong, 'A natural language generation system based on dynamic knowledge base,' Proc. of the 3rd Int. Canf. on ICSP, pp. 765-768, 1996 https://doi.org/10.1109/ICSIGP.1996.567375
  9. K. McKeown, 'Language generation: Applications, issues, and approaches,' Proc. of IEEE, vol. 74, no. 7, pp. 905-919, 1986 https://doi.org/10.1109/PROC.1986.13575
  10. H. Oh and I. Rudnicky, 'Stochastic natural language generation for spoken dialog systems,' Computer Speech and Language, vol. 16, no. 3-4, pp. 387-407, 2002 https://doi.org/10.1016/S0885-2308(02)00012-8
  11. M. Elhadad and J. Robin, 'An overview of surge: A reusable comprehensive syntactic realization component,' Technical Report 96-03, Department of Mathematics and Computer Science, 1996
  12. S. Seneff and J. Polifroni, 'Formal and natural language generation in the Mercury conversational system,' Proc. of ICSLP, vol. 2, pp. 767-770, 2000
  13. S. Bangalore and O. Rambow, 'Exploiting a probabilistic hierarchical model for generation,' Int. Canf on COLING, vol. 1, pp. 42-48, 2000 https://doi.org/10.3115/990820.990827
  14. K.-M. Kim, S.-S, Lim and S.-B. Cho, 'User adaptive answers generation for conversational agent using genetic programming,' IDEAL 2004, LNCS 3177, pp. 813-819, 2004
  15. J. Koza, Genetic Programming: Automatic Discovery of Reusable Programs, The MIT Press, 1994
  16. B. Lavoie and O. Rambow, 'A framework for customizable generation of multi-modal presentations,' COLING-AGL98, pp. 718-722, 1998
  17. L. Danlos, 'G-TAG: A lexicalized formalism for text generation inspired by tree adjoining grammar,' In Anne Abeille and Owen Rambow, editors, Tree Adjoining Grammars: Formalisms, Linguistic Analysis, and Processing, CSLI Publications. 2000
  18. C. Gardent and B. Webber, 'Varieties of ambiguity in incremental discourse processing,' Proc. of AMLap-98, 1998
  19. M. Stone and C. Doran, 'Sentence planning as description using tree adjoining grammar,' ACE/EACL 97, pp. 198-205, 1997