An Integrated Neural Network Model for Domain Action Determination in Goal-Oriented Dialogues
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
A speaker’s intentions can be represented by domain actions (domain-independent speech act and domain-dependent concept sequence pairs). Therefore, it is essential that domain actions be determined when implementing dialogue systems because a dialogue system should determine users’ intentions from their utterances and should create counterpart intentions to the users’ intentions. In this paper, a neural network model is proposed for classifying a user’s domain actions and planning a system’s domain actions. An integrated neural network model is proposed for simultaneously determining user and system domain actions using the same framework. The proposed model performed better than previous non-integrated models in an experiment using a goal-oriented dialogue corpus. This result shows that the proposed integration method contributes to improving domain action determination performance
Abstract
A speaker’s intentions can be represented by domain actions (domain-independent speech act and domain-dependent concept sequence pairs). Therefore, it is essential that domain actions be determined when implementing dialogue systems because a dialogue system should determine users’ intentions from their utterances and should create counterpart intentions to the users’ intentions. In this paper, a neural network model is proposed for classifying a user’s domain actions and planning a system’s domain actions. An integrated neural network model is proposed for simultaneously determining user and system domain actions using the same framework. The proposed model performed better than previous non-integrated models in an experiment using a goal-oriented dialogue corpus. This result shows that the proposed integration method contributes to improving domain action determination performance
참고문헌 (17)
- L. Levin, "Domain Specific Speech Acts for Spoken Language Translation", Proceedings of 4th SIGdial Workshop on Discourse and Dia-logue (2003)
- S. Carberry, "A Pragmatics-Based Approach to Ellipsis Resolution", Computational Linguistics, 15(2), pp.75~96 (1989)
- L. Lambert, "A Tripartite Plan-Based Model of Dialogue", Proceedings of ACL, pp.47~54 (1991)
- D. J. Litman, "A Plan Recognition Model for Subdialogues in Conversations", Cogni-tive Science, 11, pp.163~200 (1987)
- M. Nagata, "First Steps towards Statistical Modeling of Dialogue to Predict the Speech Act Type of the Next Utterance", Speech Communication, 15, pp.193~203 (1994)
- N. Reithinger, "Dialogue Act Classification Using Language Models", Proceedings of EuroSpeech, pp.2235~2238 (1997)
- K. Samuel, "Computing Dialogue Acts from Features with Trans-form-based Learning", Proceedings of AAAI Spring Symposium, pp.90~97 (1998)
- K. Kim, "A Neural Network Model with Feature Selection for Korean Speech Act Classification", International Journal of Neural Systems, 14(6), pp.407~414 (2004)
- H. Lee, "Domain Action Classification Using a Maximum Entropy Model in a Schedule Management Domain", AI Communications, 21(4), pp.221~229 (2008)
- S. Kang, "A Reliable Multidomain Model for Speech Act Classification", Pattern Recognition Letters, 31(1), pp.71~74 (2010)
- H. Kim, "Review of Korean Speech Act Classification : Machine Learning Methods", Journal of Computing Science and Engineering, 5(4), pp.288~293 (2011)
- D. Goddeau, "A Form-Based Dialogue Manager for Spoken Language Applications", Proceedings of International Conference on Spoken Language Processing, pp.701~704 (1996)
- Y. Yang, "A Comparative Study on Feature Selection in Text Categorization", Proceedings of the 14th International conference on Machine Learning (1997)
- D. Kim, "Speakers’ Intention Prediction using Statistics of Multi-Level Features in a Schedule Management Domain", Proceedings of ACL-08: HLT, pp.229~232 (2008)
- M. Core, "Coding Dialogues with the DAMSL Annotation Scheme", Proceedings of AAAI Fall Symposium on Communicative Action in Humans and Machines (1997)
- C. -N. Seon, "A Statistical Prediction Model of Speakers' Intentions Using Multi-level Features in a Goal-oriented Dialogue System", Pattern Recognition Letters, 33(6), pp.1397~1404 (2012)