TY - JOUR
T1 - Modeling spoken decision support dialogue and optimization of its dialogue strategy
AU - Misu, Teruhisa
AU - Sugiura, Komei
AU - Kawahara, Tatsuya
AU - Ohtake, Kiyonori
AU - Hori, Chiori
AU - Kashioka, Hideki
AU - Kawai, Hisashi
AU - Nakamura, Satoshi
PY - 2011/5
Y1 - 2011/5
N2 - This article presents a user model for user simulation and a system state representation in spoken decision support dialogue systems. When selecting from a group of alternatives, users apply different decision-making criteria with different priorities. At the beginning of the dialogue, however, users often do not have a definite goal or criteria in which they place value, thus they can learn about new features while interacting with the system and accordingly create new criteria. In this article, we present a user model and dialogue state representation that accommodate these patterns by considering the user's knowledge and preferences. To estimate the parameters used in the user model, we implemented a trial sightseeing guidance system, collected dialogue data, and trained a user simulator. Since the user parameters are not observable from the system, the dialogue is modeled as a partially observable Markov decision process (POMDP), and a dialogue state representation was introduced based on the model. We then optimized its dialogue strategy so that users can make better choices. The dialogue strategy is evaluated using a user simulator trained from a large number of dialogues collected using a trial dialogue system.
AB - This article presents a user model for user simulation and a system state representation in spoken decision support dialogue systems. When selecting from a group of alternatives, users apply different decision-making criteria with different priorities. At the beginning of the dialogue, however, users often do not have a definite goal or criteria in which they place value, thus they can learn about new features while interacting with the system and accordingly create new criteria. In this article, we present a user model and dialogue state representation that accommodate these patterns by considering the user's knowledge and preferences. To estimate the parameters used in the user model, we implemented a trial sightseeing guidance system, collected dialogue data, and trained a user simulator. Since the user parameters are not observable from the system, the dialogue is modeled as a partially observable Markov decision process (POMDP), and a dialogue state representation was introduced based on the model. We then optimized its dialogue strategy so that users can make better choices. The dialogue strategy is evaluated using a user simulator trained from a large number of dialogues collected using a trial dialogue system.
KW - Decision support systems
KW - Dialoguemanagement
KW - Reinforcement learning
KW - Spoken dialogue systems
UR - http://www.scopus.com/inward/record.url?scp=80052045386&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80052045386&partnerID=8YFLogxK
U2 - 10.1145/1966407.1966415
DO - 10.1145/1966407.1966415
M3 - Article
AN - SCOPUS:80052045386
VL - 7
JO - ACM Transactions on Speech and Language Processing
JF - ACM Transactions on Speech and Language Processing
SN - 1550-4875
IS - 3
M1 - 10
ER -