JIPS (Çѱ¹Á¤º¸Ã³¸®ÇÐȸ)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
An Integrated Neural Network Model for Domain Action Determination in Goal-Oriented Dialogues |
¿µ¹®Á¦¸ñ(English Title) |
An Integrated Neural Network Model for Domain Action Determination in Goal-Oriented Dialogues |
ÀúÀÚ(Author) |
Hyunjung Lee
Harksoo Kim
Jungyun Seo
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 09 NO. 02 PP. 0259 ~ 0270 (2013. 06) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English 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.
|
Å°¿öµå(Keyword) |
Domain Action
Speech Act
Concept Sequence
Neural Network
|
ÆÄÀÏ÷ºÎ |
|