Abstract PLANNING FOR PROBLEM FORMULATION IN ADVICE-GIVING DIALOGUE.pdfVIP

PLANNING FOR PROBLEM FORMULATION IN ADVICE-GIVING DIALOGUE Paul Decitre, Thomas Grossi, C14o Jullien, Jean-Philippe Solvay Cap Sogeti Innovation Centre de Recherche de Grenoble Chemin du Vieux Chine 38240 Meylan, France A b s t r a c t We d i s t ingu i sh th ree main , over lapping act ivi t ies in an advice-giv ing dialogue: p r o b l e m fo rmula t ion , resolut ion, and exp lana t ion . T h i s pape r focuses on a p rob lem for- mu la t ion ac t iv i ty in a d ia logue m o d u l e which in te rac t s on one side wi th an exper t p rob lem solver for financial inves t ing and on the o the r side wi th a na t u r a l l anguage front-end. Several strategies which reflect specific aspects of person-machine advice-giving dialogues are realized by incorporating planning at a high-level of dialogue. Introduction As performances and scope of intelligent systems in- crease and the interaction of a system with a user gains in complexity, it becomes desirable to provide an easy initial access to a system for the novice user. Natural language is a medium presumably known by most users. For the system however, it not only requires understanding nat- ural language utterances (on a keyboard) but also rec- ogni~.ing the intentions behind these utterances. It leads to a full-fledged dialogue involving much reasoning at the pragmatic level of the communication process. The com- petence of most intelligent systems is usually bound to a restricted application domain and we can imagine that part of a dialogue is domain-dependent while another is domain-independent. Our efforts aim at designing a dia- logue module making these different aspects explicit and interacting with other knowledge-based agents. This work contributes to Esprit Project 816 EsteamX: An architec- ture for distributed problem solving by cooperating data and knowledge bases. Advice-giving systems for financial investment have been chosen as a firs