Flexible Guidance Generation Using User Model in Spoken Dialogue Systems

Flexible Guidance Generation using User Model in Spoken Dialogue Systems Kazunori Komatani Shinichi Ueno Tatsuya Kawahara Hiroshi G. Okuno Graduate School of Informatics Kyoto University Yoshida-Hommachi, Sakyo, Kyoto 606-8501, Japan fkomatani,ueno,kawahara,okunog@kuis.kyoto-u.ac.jp Abstract We address appropriate user modeling in order to generate cooperative responses to each user in spoken dialogue systems. Un- like previous studies that focus on user’s knowledge or typical kinds of users, the user model we propose is more compre- hensive. Specifically, we set up three di- mensions of user models: skill level to the system, knowledge level on the tar- get domain and the degree of hastiness. Moreover, the models are automatically derived by decision tree learning using real dialogue data collected by the sys- tem. We obtained reasonable classifica- tion accuracy for all dimensions. Dia- logue strategies based on the user model- ing are implemented in Kyoto city bus in- formation system that has been developed at our laboratory. Experimental evalua- tion shows that the cooperative responses adaptive to individual users serve as good guidance for novice users without increas- ing the dialogue duration for skilled users. 1 Introduction A spoken dialogue system is one of the promising applications of the speech recognition and natural language understanding technologies. A typical task of spoken dialogue systems is database retrieval. Some IVR (interactive voice response) systems us- ing the speech recognition technology are being put into practical use as its simplest form. According to the spread of cellular phones, spoken dialogue sys- tems via telephone enable us to obtain information from various places without any other special appa- ratuses. However, the speech interface involves two in- evitable problems: one is speech recognition er- rors, and the other is that much information can- not be conveyed at once in speech communications. Therefore, the dialogue strategies, which determine when to make guidance and what the system should tell to the user, are the essential factors. To cope with speech recognition errors, several confirma- tion strategies have been proposed: confirmation management methods based on confidence measures of speech recognition results (Komatani and Kawa- hara, 2000; Hazen et al., 2000) and implicit con- firmation that includes previous recognition results into system’s prompts (Sturm et al., 1999). In terms of determining what to say to the user, several stud- ies have been done not only to output answers cor- responding to user’s questions but also to generate cooperative responses (Sadek, 1999). Furthermore, methods have also been proposed to change the di- alogue initiative based on various cues (Litman and Pan, 2000; Chu-Carroll, 2000; Lamel et al., 1999). Nevertheless, whether a particular response is co- operative or not depends on individual user’s char- acteristics. For example, when a user says nothing, the appropriate response should be different whether he/she is not accustomed to using the spoken dia- logue systems or he/she does not know much about the target domain. Unless we detect the cause of the silence, the system may fall into the same situation repeatedly. In order to adapt the system’s behavior to …

Content truncated to 500 words