There has been much debate, both theoretical and practical, on how to link ontologies and lexicons in natural language processing (NLP) applications. In this paper, we focus on an application in which lexicon and ontology are used to generate teaching material. We briefly describe the application (a serious game for language learning). We then zoom in on the representation and interlinking of the lexicon and of the ontology. We show how the use of existing standards and of good practice principles facilitates the design of our resources while satisfying the expressivity requirements set by natural language generation.

Cet article présente un moyen de contraindre la production d’expressions référentielles par un système de dialogue en fonction du terrain commun. Cette capacité, fondamentale pour atteindre la compréhension mutuelle, est trop souvent oubliée dans les systèmes de dialogue. Le modèle que nous proposons s’appuie sur une modélisation du processus d’ancrage (grounding process) en proposant un raffinement du statut d’ancrage appliqué à la description des référents. Il décrit quand et comment ce statut doit être révisé en fonction des jugements de compréhension des deux participants ainsi que son influence dans le choix d’une description partagée destinée à la génération d’une expression référentielle.

Cet article présente une modélisation du principe d’ancrage (grounding) pour la robustesse des systèmes de dialogue finalisés. Ce principe, décrit dans (Clark & Schaefer, 1989), suggère que les participants à un dialogue fournissent des preuves de compréhension afin d’atteindre la compréhension mutuelle. Nous explicitons une définition computationnelle du principe d’ancrage fondée sur des jugements de compréhension qui, contrairement à d’autres modèles, conserve une motivation pour l’expression de la compréhension. Nous déroulons enfin le processus d’ancrage sur un exemple tiré de l’implémentation du modèle.

Cet article décrit deux approches, l’une numérique, l’autre symbolique, traitant le problème de la résolution de la référence dans un cadre de dialogue homme-machine. L’analyse des résultats obtenus sur le corpus MEDIA montre la complémentarité des deux systèmes développés : robustesse aux erreurs et hypothèses multiples pour l’approche numérique ; modélisation de phénomènes complexes et interprétation complète pour l’approche symbolique.

This paper presents an approach to dialogue understanding based on a deep parsing and rule-based semantic analysis. Its performance in the semantic evaluation performed in the framework of the EVALDA/MEDIA campaign is encouraging. The MEDIA project aims to evaluate natural language understanding systems for French on a hotel reservation task (Devillers et al., 2004). For the evaluation, five participating teams had to produce an annotated version of the input utterances in compliance with a commonly agreed format (the MEDIA formalism). An approach based on symbolic processing was not straightforward given the conditions of the evaluation but we achieved a score close to that of statistical systems, without needing an annotated corpus. Despite the architecture has been designed for this campaign, exclusively dedicated to spoken dialogue understanding, we believe that our approach based on a LTAG parser and two ontologies can be used in real dialogue systems, providing quite robust speech understanding and facilities for interfacing with a dialogue manager and the application itself.

The aim of the Media-Evalda project is to evaluate the understanding capabilities of dialog systems. This paper presents the Media protocol for speech understanding evaluation and describes the results of the June 2005 literal evaluation campaign. Five systems, both symbolic or corpus-based, participated to the evaluation which is based on a common semantic representation. Different scorings have been performed on the system results. The understanding error rate, for the Full scoring is, depending on the systems, from 29% to 41.3%. A diagnosis analysis of these results is proposed.

An unified language for the communicative acts between agents is essential for the design of multi-agents architectures. Whatever the type of interaction (linguistic, multimodal, including particular aspects such as force feedback), whatever the type of application (command dialogue, request dialogue, database querying), the concepts are common and we need a generic meta-model. In order to tend towards task-independent systems, we need to clarify the modules parameterization procedures. In this paper, we focus on the characteristics of a meta-model designed to represent meaning in linguistic and multimodal applications. This meta-model is called MMIL for MultiModal Interface Language, and has first been specified in the framework of the IST MIAMM European project. What we want to test here is how relevant is MMIL for a completely different context (a different task, a different interaction type, a different linguistic domain). We detail the exploitation of MMIL in the framework of the IST OZONE European project, and we draw the conclusions on the role of MMIL in the parameterization of task-independent dialogue managers.