Learning to control listening-oriented dialogue using partially observable markov decision processes

被引：0

作者：

Meguro, Toyomi ^{[1
]}

Minami, Yasuhiro ^{[1
]}

Higashinaka, Ryuichiro ^{[2
]}

Dohsaka, Kohji ^{[2
]}

机构：

[1] Meguro, Toyomi

[2] Minami, Yasuhiro

[3] Higashinaka, Ryuichiro

[4] Dohsaka, Kohji

来源：

Meguro, T. (meguro.toyomi@lab.ntt.co.jp) | 1600年 / Association for Computing Machinery卷 / 10期

基金：

日本学术振兴会;

关键词：

Dialogue control; Dialogue systems; Listening-oriented dialogue; Partially observable Markov decision processes;

D O I：

10.1145/2513145

中图分类号：

学科分类号：

摘要：

Our aim is to build listening agents that attentively listen to their users and satisfy their desire to speak and have themselves heard. This article investigates how to automatically create a dialogue control component of such a listening agent.We collected a large number of listening-oriented dialogues with their user satisfaction ratings and used them to create a dialogue control component that satisfies users by means of Partially Observable Markov Decision Processes (POMDPs). Using a hybrid dialog controller where high-level dialog acts are chosen with a statistical policy and low-level slot values are populated by a wizard, we evaluated our dialogue control method in aWizard-of-Oz experiment. The experimental results show that our POMDPbased method achieves significantly higher user satisfaction than other stochastic models, confirming the validity of our approach. This article is the first to verify, by using human users, the usefulness of POMDPbased dialogue control for improving user satisfaction in nontask-oriented dialogue systems. © 2013 ACM 1550-4875/2013/12-ART17 15.00.

引用

共 40 条

[1]

Bickmore T., Cassell J., Relational agents: A model and implementation of building user trust, Proceedings Of The Acm Conference On Human Factors In Computing Systems (Chi'01), pp. 396-403, (2001)

[2]

Boularias A., Chinaei H.R., Chaib-Draa B., Learning the reward model of dialogue pomdps from data, Proceedings Of The Nips Workshop Of Machine Learning For Assistive Techniques, pp. 1-9, (2010)

[3]

Cohen J., A coefficient of agreement for nominal scales, Educ. Psychol. Measur, 43, pp. 37-46, (1960)

[4]

Cohen W.W., Carvalho V.R., Mitchell T.M., Learning to classify email into, Proceedings Of The Conference On Empirical Methods In Natural Language Processing (Emnlp'04), pp. 309-316, (2004)

[5]

Core M., Allen J., Coding dialogs with the damsl annotation scheme, Proceedings Of The Working Notes Of The Aaai Fall Symposium On Communicative Action In Humans And Machines, (1997)

[6]

Ferguson G., Allen J.F., Miller B., Trains-95: Towards a mixed-initiative planning assistant, Proceedings Of The 3Rd Conference On Ai Planning Systems, pp. 70-77, (1996)

[7]

Gasi C.M., Jurcicek F., Thomson B., Yu K., Young S., On-line policy optimisation of spoken dialogue systems via live interaction with human subjects, Proceedings Of IEEEworkshop On Automatic Speech Recognition And Understanding (Asru'11), pp. 312-317, (2011)

[8]

Higashinaka R., Dohsaka K., Isozaki H., Effects of self-disclosure and empathy in human computer dialogue, Proceedings Of The Spoken Language Technology Workshop (Slt'08), pp. 108-112, (2008)

[9]

Higashinaka R., Minami Y., Dohsaka K., Meguro T., Issues in predicting user satisfaction transitions in dialogues: Individual differences, evaluation criteria, and prediction models, Proceedings Of The 2Nd International Conference On Spoken Dialogue Systems For Ambient Environments, pp. 48-60, (2010)

[10]

Higuchi S., Rzepka R., Araki K., A casual conversation system using modality and word associations retrieved from the web, Proceedings Of The Conference On Empirical Methods In Natural Language Processing (Emnlp'08), pp. 382-390, (2008)

← 1 2 3 4 →