Bringing Statistical Methodologies for Enterprise Integration of Conversational Agents

In this paper we present a methodology to develop commercial conversational agents that avoids the effort of manually defining the dialog strategy for the dialog management module. Our corpus-based methodology is based on selecting the next system answer by means of a classification process in which the complete dialog history is considered. This way, system developers can employ standards like VoiceXML to simply define system prompts and the associated grammars to recognize the users responses to the prompt, and the statistical dialog model automatically selects the next system prompt.We have applied this methodology for the development of an academic conversational agent.

[1]  Ramón López-Cózar,et al.  Relations between de-facto criteria in the evaluation of a spoken dialogue system , 2008, Speech Commun..

[2]  Laurent Mazuel,et al.  Generic Command Interpretation Algorithms for Conversational Agents , 2006, 2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology.

[3]  Alexander I. Rudnicky,et al.  LARRI: A Language-Based Maintenance and Repair Assistant , 2005 .

[4]  Gérard Bailly,et al.  Gaze, conversational agents and face-to-face communication , 2010, Speech Commun..

[5]  Steve Young,et al.  A data-driven spoken language understanding system , 2003, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721).

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

[7]  David Griol,et al.  Acquiring and Evaluating a Dialog Corpus through a Dialog Simulation Technique , 2007, SIGdial.

[8]  Steve Young,et al.  The statistical approach to the design of spoken dialogue systems , 2003 .

[9]  Toni Giorgino,et al.  Adaptable dialog architecture and runtime engine (AdaRTE): A framework for rapid prototyping of health dialog systems , 2009, Int. J. Medical Informatics.

[10]  Rohit Kumar,et al.  Conquestâ - An Open-Source Dialog System for Conferences , 2007, HLT-NAACL.

[11]  Victor Zue,et al.  Multilingual spoken-language understanding in the MIT Voyager system , 1995, Speech Commun..

[12]  H. Bratt,et al.  CHAT: a conversational helper for automotive tasks , 2006, INTERSPEECH.

[13]  Paulo Menezes,et al.  Towards an Interactive Humanoid Companion with Visual Tracking Modalities , 2007 .

[14]  Encarna Segarra,et al.  Error handling in a stochastic dialog system through confidence measures , 2005, Speech Commun..

[15]  Leon G. Higley,et al.  Forensic Entomology: An Introduction , 2009 .

[16]  Victor Zue,et al.  JUPlTER: a telephone-based conversational interface for weather information , 2000, IEEE Trans. Speech Audio Process..

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

[18]  Alex Waibel,et al.  Stochastically-Based Semantic Analysis , 1999 .

[19]  Hakan Melin,et al.  CTT-bank: A speech controlled telephone banking system - an initial evaluation , 2007 .

[20]  Sheryl Brahnam,et al.  Building Character for Artificial Conversational Agents: Ethos, Ethics, Believability, and Credibility , 2009, PsychNology J..

[21]  C. Vaquero,et al.  VOCALIZA: AN APPLICATION FOR COMPUTER-AIDED SPEECH THERAPY IN SPANISH LANGUAGE , 2006 .

[22]  Masahiro Araki,et al.  Spoken, Multilingual and Multimodal Dialogue Systems: Development and Assessment , 2005 .