DOI QR코드

DOI QR Code

목적지향 대화 시스템을 위한 챗봇 연구

A Chatter Bot for a Task-Oriented Dialogue System

  • 황금하 (한국전자통신연구원 언어지능연구그룹) ;
  • 권오욱 (한국전자통신연구원 언어지능연구그룹) ;
  • 이경순 (전북대학교 컴퓨터공학부) ;
  • 김영길 (한국전자통신연구원 언어지능연구그룹)
  • 투고 : 2017.08.01
  • 심사 : 2017.08.22
  • 발행 : 2017.11.30

초록

목적 지향 대화 시스템에서 자유대화를 지원하기 위해 챗봇이 활용되고 있다. 그러나 목적지향 대화시스템을 위한 챗봇과 독립 챗봇에 대한 사용자 기대와 평가가 같은지에 대한 연구는 거의 없는 상황이다. 본 논문에서는 목적지향 대화시스템으로 구현한 영어 교육용 대화시스템에서, 대화의 자유도를 높이기 위하여 주제외 사용자 발화를 허용하고, 이에 대응하기 위한 챗봇을 개발하였다. 독립 챗봇과 보조 시스템으로서의 챗봇에 대하여 비교 평가함으로, 서로 다른 시스템에 대한 사용자의 서로 다른 기대를 살펴보았다. 또한 검색 기반 챗봇과 신경망 기술을 이용한 생성 기반 챗봇에 대한 비교 평가를 통해 이들의 장단점과 향후 활용 방안에 대하여 살펴보았다.

Chatter bots are normally used in task-oriented dialogue systems to support free conversations. However, there is not much research on how chatter bots as auxiliary system should be different from independent ones. In this paper, we have developed a chatter bot for a dialogue-based computer assisted language learning (DB-CALL) system. We compared the chatter bot in two different cases: as an independent bot, and as an auxiliary system. The results showed that, the chatter bot as an auxiliary system showed much lower satisfaction than the independent one. A discussion is held about the difference between an auxiliary chatter bot and an independent bot. In addition, we evaluated a search-based chatter bot and a deep learning based chatter bot. The advantages and disadvantages of both methods are discussed.

키워드

참고문헌

  1. Apple Siri [Internet], https://www.apple.com/kr/ios/siri/.
  2. Amazon Alexa[Internet], https://developer.amazon.com/alexa
  3. Houndify[Internet], https://www.houndify.com/.
  4. O.-W. Kwon, T.-K. Hong, J.-X. Huang, and Y.-K. Kim "Virtual personal assistant: dialogue processing technique and recent trends," Communications of the Korean Institute of Information Scientists and Engineers, Vol.35, No.8, pp.19-27, 2017.
  5. A. Raux and M. Eskenazi, "A finite-state turn-taking model for spoken dialog systems," Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the ACL, Boulder, Colorado, pp.629-637, 2009.
  6. D. Goddeau, H. Meng, J. Polifroni, S. Seneff, and S. Busayapongchai, "A form-based dialogue manager for spoken language applications," in Proceedings of International Conference of Speech Language Processing, Philadelphia, PA, 1996.
  7. I. Ahmed and S. Singh, "AIML based voice enabled artificial intelligent chatterbot," International Journal of u- and e-Service, Science and Technology Vol.8, No.2, pp.375-384, 2015. https://doi.org/10.14257/ijunesst.2015.8.2.36
  8. C. Lee, S. Jung, S. Kim, and G. Lee, "Example-based dialog modeling for practical multi-domain dialog system," Speech Communications, Vol.51, No.5, pp.466-484, 2009. https://doi.org/10.1016/j.specom.2009.01.008
  9. A. Ritter, C. Cherry, and W. B. Dolan, "Data-driven response generation in social media," in Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp.583-593, 2011.
  10. S. Jung, S.-H. Na, "Refining sentence similarity with discourse information in dialog system," in Proceedings of INTERSPEECH, 2013.
  11. R. Yan, Y. Song, and H. Wu, "Learning to respond with deep neural networks for retrieval-based human-computer converstaion system," in Proceedings of SIGIR'16, Pisa, Italy, 2016.
  12. I. Sutskever, O. Vinyals, and Q. Le, "Sequence to sequence learning with neural networks," in Proceedings of NIPS, 2014.
  13. O. Vinyals and Q. Le, "A neural conversational model," Proceedings of the 31 st International Conference on Machine Learning, Deep Learning Workshop, 2015.
  14. J. Bang, H Noh, Y. Kim, and G. Lee, "Example-based chat-oriented dialogue system," in Proc. BigComp pp.238-243. 2015.
  15. ChatScript [Internet], http://chatscript.sourceforge.net/.
  16. O.-W. Kwon, K. Lee, Y.-H. Roh, J.-X. Huang, S.-K. Choi, Y.-K. Kim, H.B. Jeon, Y. R. Oh, Y.-K. Lee, B.O. Kang, E. Chung, J.G. Park, and Y. Lee, "GenieTutor: a computer assisted second-language learning system based on spoken language understanding," in Proceedings of the 2015 International Workshop on Spoken Dialogue Systems, 2015.
  17. J.-X. Huang, K.-S. Lee., O.-W. Kwon, and Y.-K. Kim, "Automatic dialogue scoring for a second language learning system," in S. Papadima-Sophocleous, L. Bradley & S. Thouesny (Eds), CALL Communities and Culture-Short Papers from EUROCALL, pp.1-6, 2016.
  18. S.-K. Choi, , O.-W. Kwon, Y.-K. Kim, and Y. Lee, "Using a dialogue system based on dialogue maps for computer assisted second language learning," in S. Papadima-Sophocleous, L. Bradley & S. Thouesny (Eds), CALL Communities and Culture. Short papers from EUROCALL, pp.1-7, 2016.
  19. R. E. Banchs, "MovieDic: a movie dialogue corpus for research and development," in Proceedings of ACL, pp.203-207, 2012.
  20. BNC [Internet], http://www.natcorp.ox.ac.uk/.
  21. T. Strohman, D. Metzler, H. Turtle, and W. B. Croft, "Indri: a language model-based search engine for complex queries," in Proceedings of the International Conference on Intelligence Analysis, 2005.
  22. C. X. Zhai, "Notes on the Lemur TFIDF model" [Internet], http://www.lemurproject.org/lemur/tfidf.pdf, 2001.
  23. G. Klein, Y. Kim, Y. Deng, J. Senellart, and A. M. Rush. "OpenNMT: open-source toolkit for neural machine translation" [Internet], CoRR, abs/1701.02810, http://arxiv.org/abs/1701.02810. 2017.
  24. S.-K. Choi, O.-W. Kwon, K. Lee, Y.-H. Noh, J.-X. Huang, and Y.-K. Kim "English education system using a chatter bot and a dialogue system," in Proceedings of Spring Conference of KIPS, 2017.