Online Learning of Stochastic Bi-automaton to Model Dialogues

The Interactive Pattern Recognition framework has been proposed to deal with Spoken Dialog Systems. In this framework the joint probability distribution over some semantic language provided by the speech understanding system and the language of actions provided by the Dialog Manager have been modeled by stochastic regular bi-languages. In this work we propose an algorithm to estimate the parameters of the corresponding Probabilistic Finite State Bi-Automaton. Moreover an on line learning methodology aimed at updating the model parameters at each interaction step is also proposed. The experimental evaluation carried out with different simulated users over LetsGo task shows the learning and adaptation capabilities of the proposal.

[1]  Maxine Eskénazi,et al.  Let's go public! taking a spoken dialog system to the real world , 2005, INTERSPEECH.

[2]  David Griol,et al.  A stochastic finite-state transducer approach to spoken dialog management , 2010, INTERSPEECH.

[3]  Fabrizio Ghigi,et al.  Modeling Spoken Dialog Systems under the Interactive Pattern Recognition Framework , 2012, SSPR/SPR.

[4]  Fabrizio Ghigi,et al.  Evaluating spoken dialogue models under the interactive pattern recognition framework , 2013, INTERSPEECH.

[5]  Andrés Colmena Asensio,et al.  Electricidad y Electrónica , 1999 .

[6]  M. Inés Torres.  Stochastic Bi-Languages to model Dialogs , 2013, FSMNLP.

[7]  Alexander I. Rudnicky,et al.  The RavenClaw dialog management framework: Architecture and systems , 2009, Comput. Speech Lang..

[8]  Milica Gasic,et al.  Bayesian dialogue system for the Let's Go Spoken Dialogue Challenge , 2010, 2010 IEEE Spoken Language Technology Workshop.

[9]  Oliver Lemon,et al.  Evaluation of a hierarchical reinforcement learning spoken dialogue system , 2010, Comput. Speech Lang..

[10]  M. Inés Torres,et al.  Stochastic K-TSS Bi-Languages for Machine Translation , 2011, FSMNLP.

[11]  Fabrizio Ghigi,et al.  Decision Making Strategies for Finite-State Bi-automaton in Dialog Management , 2015, Natural Language Dialog Systems and Intelligent Assistants.

[12]  Milica Gasic,et al.  POMDP-Based Statistical Spoken Dialog Systems: A Review , 2013, Proceedings of the IEEE.

[13]  Steve J. Young,et al.  Partially observable Markov decision processes for spoken dialog systems , 2007, Comput. Speech Lang..

[14]  Steve J. Young,et al.  Reinforcement learning for parameter estimation in statistical spoken dialogue systems , 2012, Comput. Speech Lang..

[15]  David Griol,et al.  A statistical approach to spoken dialog systems design and evaluation , 2008, Speech Commun..

[16]  Francisco Casacuberta,et al.  Multimodal Interactive Pattern Recognition and Applications , 2011 .

[17]  Oliver Lemon,et al.  Author manuscript, published in "European Conference on Speech Communication and Technologies (Interspeech'07), Anvers: Belgium (2007)" Machine Learning for Spoken Dialogue Systems , 2022 .

[18]  Roberto Pieraccini,et al.  The use of belief networks for mixed-initiative dialog modeling , 2000, IEEE Trans. Speech Audio Process..

[19]  Melita Hajdinjak,et al.  The PARADISE Evaluation Framework: Issues and Findings , 2006, Computational Linguistics.

[20]  Michael Picheny,et al.  A Comparison of Rule-Based and Statistical Methods for Semantic Language Modeling and Confidence Measurement , 2004, HLT-NAACL.