Dialogue management for leading the conversation in persuasive dialogue systems

Author

Hiraoka, Toru ; Yamauchi, Yuji ; Neubig, Graham ; Sakti, Sakriani ; Toda, Takechi ; Nakamura, Shigenari

Author_Institution

Grad. Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Nara, Japan

fYear

2013

fDate

8-12 Dec. 2013

Firstpage

114

Lastpage

119

Abstract

In this research, we propose a probabilistic dialogue modeling method for persuasive dialogue systems that interact with the user based on a specific goal, and lead the user to take actions that the system intends from candidate actions satisfying the user´s needs. As a baseline system, we develop a dialogue model assuming the user makes decisions based on preference. Then we improve the model by introducing methods to guide the user from topic to topic. We evaluate the system knowledge and dialogue manager in a task that tests the system´s persuasive power, and find that the proposed method is effective in this respect.

Keywords

interactive systems; knowledge based systems; probability; speech processing; speech-based user interfaces; dialogue management; persuasive dialogue system; probabilistic dialogue modeling; system knowledge; Bayes methods; Knowledge based systems; Laboratories; Mutual information; Probabilistic logic; Speech; Web search; Dialogue management; Estimating user´s preference; Leading conversations; Persuasive dialogue; Spoken dialogue system;

fLanguage

English

Publisher

ieee

Conference_Titel

Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on

Conference_Location

Olomouc

Type

conf

DOI

10.1109/ASRU.2013.6707715

Filename

6707715