Managing out-of-grammar utterances by topic estimation with domain extensibility in multi-domain spoken dialogue systems

Spoken dialogue systems must inevitably deal with out-of-grammar utterances. We address this problem in multi-domain spoken dialogue systems, which deal with more tasks than a single-domain system. We defined a topic by augmenting a domain about which users want to find more information, and we developed a method of recovering out-of-grammar utterances based on topic estimation, i.e., by providing a help message in the estimated domain. Moreover, domain extensibility, that is, the ability to add new domains to the system, should be inherently retained in multi-domain systems. To estimate domains without sacrificing extensibility, we collected documents from the Web as training data. Since the data contained a certain amount of noise, we used latent semantic mapping (LSM), which enables robust topic estimation by removing the effects of noise from the data. Experimental results showed that our method improved topic estimation accuracy by 23.2 points for data including out-of-grammar utterances.

[1]  Tetsuya Ogata,et al.  Dynamic help generation by estimating user²s mental model in spoken dialogue systems , 2006, INTERSPEECH.

[2]  Tatsuya Kawahara,et al.  User Modeling in Spoken Dialogue Systems to Generate Flexible Guidance , 2004, User Modeling and User-Adapted Interaction.

[3]  Manny Rayner,et al.  Adding intelligent help to mixed-initiative spoken dialogue systems , 2002, INTERSPEECH.

[4]  Tatsuya Kawahara,et al.  A bootstrapping approach for developing language model of new spoken dialogue systems by selecting web texts , 2006, INTERSPEECH.

[5]  Bob Carpenter,et al.  Dialogue Management in Vector-Based Call Routing , 1998, ACL.

[6]  Tetsuya Ogata,et al.  Introducing Utterance Verification in Spoken Dialogue System to Improve Dynamic Help Generation for Novice Users , 2007, SIGdial.

[7]  Naoyuki Kanda,et al.  Multi-Domain Spoken Dialogue System with Extensibility and Robustness against Speech Recognition Errors , 2006, SIGDIAL Workshop.

[8]  Lin-Shan Lee,et al.  A Distributed Agent Architecture for Intelligent Mulit-Domain Spoken Dialogue Systems , 2001 .

[9]  Pascal Poupart,et al.  Factored partially observable Markov decision processes for dialogue management , 2005 .

[10]  Oliver Lemon,et al.  Targeted help for spoken dialogue systems: intelligent feedback improves naive users' performance , 2003 .

[11]  Naoyuki Kanda,et al.  A two-layer model for behavior and dialogue planning in conversational service robots , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Michael F. McTear,et al.  Cross domain dialogue modelling: an object-based approach , 2004, INTERSPEECH.

[13]  Maxine Eskénazi,et al.  Non-Native Users in the Let’s Go!! Spoken Dialogue System: Dealing with Linguistic Mismatch , 2004, NAACL.

[14]  Stephanie Seneff,et al.  Automatic induction of language model data for a spoken dialogue system , 2006, SIGDIAL.

[15]  Bob Carpenter,et al.  A portable, server-side dialog framework for voiceXML , 2002, INTERSPEECH.

[16]  Satoshi Nakamura,et al.  Topic classification and verification modeling for out-of-domain utterance detection , 2004, INTERSPEECH.

[17]  Jerome Rene Bellegarda,et al.  Latent Semantic Mapping , 2007 .

[18]  J.R. Bellegarda,et al.  Latent semantic mapping [information retrieval] , 2005, IEEE Signal Processing Magazine.

[19]  Alexander I. Rudnicky,et al.  Sorry and I Didn’t Catch That! - An Investigation of Non-understanding Errors and Recovery Strategies , 2005, SIGDIAL.

[20]  Botond Pakucs.  Towards dynamic multi-domain dialogue processing , 2003, INTERSPEECH.

[21]  Chin-Hui Lee,et al.  Dialogue session: management using voiceXML , 2001, INTERSPEECH.