Content uploaded by François Bouchet
Author content
All content in this area was uploaded by François Bouchet
Content may be subject to copyright.
A preview of the PDF is not available
Définition d'un agent conversationnel assistant d'applications internet à partir d'un corpus de requêtes.
Abstract and Figures
RÉSUMÉ. Les Agents Conversationnels Assistants sont une sous-classe des Agents Conversationnels Animés, dédiée à la Fonction d'Assistance pour les applications et services du grand public. Les nouvelles applications Internet sont un domaine particulièrement intéressant pour étudier les agents assistants pour le grand public. Nous avons donc développé un logiciel orienté Web, appelé le « toolkit DIVA », où la Fonction d'Assistance est une question clé et où la Langue Naturelle joue un rôle essentiel. C'est la raison pour laquelle le toolkit DIVA repose sur une chaîne de Traitement Automatique de la Langue Naturelle (TALN) qui est chargée de traiter des requêtes d'assistance. Dans ce contexte, les outils de TALN ainsi que les outils d'assistance devraient être simples et faciles à déployer pour chaque nouvelle application Web assistée par un agent DIVA. Notre proposition repose sur le recueil d'un corpus de requêtes d'assistance qui permet d'une part de circonscrire le domaine de langue concerné et d'autre part d'éliciter les principaux phénomènes linguistiques qui occurrent effectivement. Sur cette base, nous avons défini une architecture de chaîne de traitement qui a été implémentée dans le toolkit DIVA ; elle a ensuite été mise à l'épreuve sur plusieurs applications test. ABSTRACT. Assisting Conversational Agents are Embodied Conversational Agents dedicated to the Function of Assistance for applications and services to the general public. Assisting agents for the general public are more and more required on the Internet-based new applications. We have developed a web-based framework to experiment with assisting agents, called the DIVA toolkit, where the Function of Assistance is a key issue, and the Natural Language modality is a primary concern. This is why the DIVA toolkit is based on a Natural Language Processing chain (NLP-chain) handling the users' textual help requests. In this context, both the NLP-chain tools and the assistance tools should be simple and easy to deploy for each new Web application assisted by the DIVA agents. Our proposition relies on the collection of a corpus of assisting requests which firstly enables us to circumscribe the domain of assistance and secondly makes it possible to exhibit the main occurring linguistic phenomena. On this basis, the architecture of a NLP-chain has been defined and implemented in the DIVA toolkit; then it has been put to test on several small applications.
Figures - uploaded by François Bouchet
Author content
All figure content in this area was uploaded by François Bouchet
Content may be subject to copyright.
... This architecture will be based on previous works on Conversational Assistant Agents (Sansonnet 1999, Sansonnet at al. 2002) and more precisely on the DIVA toolkit. Actually DIVA stands for DOM-Integrated Virtual Agents, which emphasizes the unique feature of DIVA agents to interact in natural language with users and to control directly the inner structure of the content of the Web page they assist (Bouchet and Sansonnet 2007, Xuetao et al. 2011). Figure 1-left shows a typical DIVA assisted Web page. ...
Nowadays, ordinary people can freely access a large amount of information through Internet. Then issues of production and transport of computational entities are superseded by new requirements like: enticement, acceptability and understanding. To achieve these goals, we propose an approach based on dialogical interaction between novice users and conversational agents achieving the mediation of computational entities. The originality of the approach is based on the principle of personification of an entity by an agent, where the agent and the entity share a single identity.
... Globalement, dans la partie rationnelle du modèle, on enregistre la valeur absolue (Rateunempl-F ) et la différence entre les deux courbes du graphique pour les deux pays (Dif-unempl-FS, Dif-unempl-FI) alors que dans la partie psychologique , deux attributs mentaux appartenant à la sous-partie mood) du modèle de l'agent sont liés aux écarts avec les deux pays de la manière suivante (les lettres correspondant au taux de chômage pour le pays ayant cette initiale) : discuté à la section 2.4. Nous utilisons cidessous des expressions tirées du personnage 'Cyril' qui fait partie du toolkit DIVA présenté plus haut [46]. Par exemple, on pourra avoir la réponse multimodale suivante (c'est nous qui soulignons l'ajout du mot 'malheureusement') : ...
La question de l'accès à l'information ne se pose plus tant en termes de la production et du transport qu'en termes d'accroche, d'acceptabilité et d'assimilation auprès du grand public qui utilise massivement l'Internet. Pour ce faire, nous proposons une approche fondée sur la notion d'interaction dialogique entre un usager novice et un agent conversationnel chargé de médier des entités computationnelles. L'originalité de l'approche repose sur le principe de personnalisation d'une entité au moyen d'un agent qui s'identifie à elle.
A Conversational Agent can be useful for providing assistance to naïve users on how to use a graphical interface. Such an assistant requires three features: understanding users' requests, reasoning, and intuitive output. In this paper we introduce the DAFT-LEA architecture for enabling assistant agents to reply to questions asked by naive users about the structure and functioning of graphical interfaces. This architecture integrates via a unified software engineering approach a linguistic parser for the understanding the user's requests, a rational agent for the reasoning about the graphical application, and a 2D cartoon like agent for the multimodal output. We describe how it has been applied to three different assistance application contexts, and how it was incrementally defined via the collection of a corpus of users' requests for assistance. Such an approach can be useful for the design of other assistance applications since it enables a clear separation between the original graphical application, its abstract DAFT model and the linguistic processing of users' requests.
One of the most sweeping changes ever in the ecology of human cognition may be taking place today. People are beginning to learn and use very powerful and sophisticated information processing technology as a matter of daily life. From the perspective of human history, this could be a transitional point dividing a period when machines merely helped us do things from a period when machines will seriously help us think about things. But if this is so, we are indeed still very much within the transition. For most people, computers have more possibility than they have real practical utility.
It is well-known that there are polysemous words like sentence whose "meaning" or "sense" depends on the context of use. We have recently reported on two new word-sense disambiguation systems, one trained on bilingual material (the Canadian Hansards) and the other trained on monolingual material (Roget's Thesaurus and Grolier's Encyclopedia). As this work was nearing completion, we observed a very strong discourse effect. That is, if a polysemous word such as sentence appears two or more times in a well-written discourse, it is extremely likely that they will all share the same sense. This paper describes an experiment which confirmed this hypothesis and found that the tendency to share sense in the same discourse is extremely strong (98%). This result can be used as an additional source of constraint for improving the performance of the word-sense disambiguation algorithm. In addition, it could also be used to help evaluate disambiguation algorithms that did not make use of the discourse constraint.
La modélisation formelle de l’interaction entre les usagers grand public et les systèmes informatiques a un rôle crucial à jouer au niveau de la Fonction d’Assistance. Il s’agit préalablement de caractériser sémantiquement, en termes de couverture et de précision, des phénomènes liés à l’assistance pour proposer à terme un agent rationnel assistant générique capable de réactions pertinentes aux requêtes des usagers. Dans cet article, nous présentons notre approche de construction d’un langage pour des agents conversationnels assistants, basée sur l’étude préalable d’un corpus de requêtes recueillies dans des situations effectives d’assistance. --- Formal modeling of the interaction between ordinary users and computer-based systems has a major part to play in the Assistance Function. A first objective is to characterize semantically, both in coverage and precision, the phenomena associated with the Assistance Function to provide a generic assisting rational agent capable of pertinent reactions to users’ requests. In this paper, we present our approach to the construction of a language for a class of assisting conversational agents, based on the study of a corpus of users’ requests registered in actual assisting experimentations.
In this paper we review studies of the growth of the Internet and technologies that are useful for information search and retrieval on the Web. We present data on the Internet from several different sources, e.g., current as well as projected number of users, hosts, and Web sites. Although numerical figures vary, overall trends cited by the sources are consistent and point to exponential growth in the past and in the coming decade. Hence it is not surprising that about 85% of Internet users surveyed claim using search engines and search services to find specific information. The same surveys show, however, that users are not satisfied with the performance of the current generation of search engines; the slow retrieval speed, communication delays, and poor quality of retrieved results (e.g., noise and broken links) are commonly cited problems. We discuss the development of new techniques targeted to resolve some of the problems associated with Web-based information retrieval,and speculate on future trends. Categories and Subject Descriptors: G.1.3 [Numerical Analysis]: Numerical Linear Algebra-Eigenvalues and eigenvectors (direct and iterative methods); Singular value decomposition; Sparse, structured and very large systems (direct and iterative methods); G.I.I [Numerical Analysis]: Interpolation; H.3.1 [Information Storage and Retrieval]: Content Analysis and Indexing; H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval-Clustering; Retrieval models; Search process; H.m [Information Systems]: Miscellaneous General Terms: Algorithms, Theory.
Part I. A Theory of Speech Acts: 1. Methods and scope 2. Expressions, meaning and speech acts 3. The structure of illocutionary acts 4. Reference as a speech act 5. Predication Part II. Some Applications of the Theory: 6. Three fallacies in contemporary philosophy 7. Problems of reference 8. Deriving 'ought' from 'is' Index.
Colloque avec actes et comité de lecture. internationale.
In designing computer-based systems, we work within a perspective that shapes the design questions that will be asked and the kinds of solutions that are sought. This paper introduces a perspective based on language as action, and explores its consequences for practical system design. The language/action perspective is contrasted to a number of other currently prominent perspectives, and is illustrated with an extended example based on studies of nursing work in a hospital ward. We show how it leads to particular analyses of that work, which reveal potentials for creating new designs that can make the work (and the workers) more effective.