Generic command interpretation algorithms for conversational agents

This paper focuses on human-machine communication with intelligent agents, it proposes a generic architecture with an algorithm for natural language (NL) command interpretation which makes it easy to define different applications using the description and domains of the different agents, since all that is required is their respective codes and domain ontologies. There are two classical approaches for NL command interpretation: the top-down approach, which relies on the syntactical constraints of the agent's model, and the bottom-up approach which relies on the set of the agent's possible actions. The present work combines the two in a new bottom-up based algorithm that makes use of agent's constraints. The three algorithms are then compared, and results show that the combined approach gives best results.

[1]  Roy Rada,et al.  Development and application of a metric on semantic nets , 1989, IEEE Trans. Syst. Man Cybern..

[2]  Candace L. Sidner,et al.  COLLAGEN: Applying Collaborative Discourse Theory to Human-Computer Interaction , 2001, AI Mag..

[3]  Catherine Pelachaud,et al.  Modelling Gaze Behaviour for Conversational Agents , 2003, IVA.

[4]  Cesar Augusto Tacla,et al.  A Speech Architecture for Personal Assistants in a Knowledge Management Context , 2004, ECAI.

[5]  Nati Herrasti,et al.  GENIO: an ambient intelligence application in home automation and entertainment environment , 2005, sOc-EUSAI '05.

[6]  Iryna Gurevych,et al.  Less is More: Using a single knowledge representation in dialogue systems , 2003, HLT-NAACL 2003.

[7]  John A. Bateman,et al.  Enabling technology for multilingual natural language generation: the KPML development environment , 1997, Natural Language Engineering.

[8]  Iryna Gurevych,et al.  Ontology-based Contextual Coherence Scoring , 2003, SIGDIAL Workshop.

[9]  Stephanie Seneff,et al.  TINA: A Natural Language System for Spoken Language Applications , 1992, Comput. Linguistics.

[10]  Nicolas Sabouret,et al.  An agent interaction protocol for ambient intelligence , 2006 .

[11]  Jacques Ferber,et al.  Multi-agent systems - an introduction to distributed artificial intelligence , 1999 .

[12]  Laurent Mazuel,et al.  Degré de relation sémantique dans une ontologie pour la commande en langue naturelle , 2007, Actes d'IC.

[13]  J. Cassell,et al.  Embodied conversational agents , 2000 .

[14]  W. Rapaport,et al.  The SNePS family , 1992 .

[15]  Terry Winograd,et al.  Understanding natural language , 1974 .

[16]  Karolina Eliasson,et al.  Case-Based Techniques Used for Dialogue Understanding and Planning in a Human-Robot Dialogue System , 2007, IJCAI.

[17]  David Milward.  Distributing Representation for Robust Interpretation of Dialogue Utterances , 2000, ACL.

[18]  Graeme Hirst,et al.  Evaluating WordNet-based Measures of Lexical Semantic Relatedness , 2006, CL.

[19]  Annika Flycht-Eriksson.  Design of Ontologies for Dialogue Interaction and Information Extraction , 2003 .

[20]  Arnaud Gotlieb,et al.  Utilisation des contraintes pour la génération automatique de cas de test structurels , 2002, Tech. Sci. Informatiques.

[21]  James F. Allen,et al.  TRIPS: An Integrated Intelligent Problem-Solving Assistant , 1998, AAAI/IAAI.

[22]  Wolfgang Wahlster,et al.  SmartKom: Symmetric Multimodality in an Adaptive and Reusable Dialogue Shell , 2003 .

[23]  Philippe Bretier,et al.  ARTIMIS: Natural Dialogue Meets Rational Agency , 1997, IJCAI.

[24]  Charles J. Fillmore,et al.  The FrameNet tagset for frame-semantic and syntactic coding of predicate-argument structure , 2000, ANLP.

[25]  David W. Conrath,et al.  Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy , 1997, ROCLING/IJCLCLP.

[26]  Timothy W. Bickmore.  Unspoken rules of spoken interaction , 2004, CACM.

[27]  Pattie Maes,et al.  Agents that reduce work and information overload , 1994, CACM.

[28]  Eric K. Ringger,et al.  A Robust System for Natural Spoken Dialogue , 1996, ACL.