tailieunhanh - Báo cáo khoa học: "A FLEXIBLE APPROACH TO COOPERATIVE RESPONSE GENERATION IN INFORMATION-SEEKING DIALOGUES"

This paper presents a cooperative consultation system on a restricted domain. The system builds hypotheses on the user's plan and avoids misunderstandings (with consequent repair dialogues) through clarification dialogues in case of ambiguity. The role played by constraints in the generation of the answer is characterized in order to limit the cases of ambiguities requiring a clarification dialogue. The answers of the system are generated at different levels of detail, according to the user's competence in the domain. . | A FLEXIBLE APPROACH TO COOPERATIVE RESPONSE GENERATION IN INFORMATION-SEEKING DIALOGUES Liliana Ardissono Alessandro Lombardo Dario Sestero Dipartimento di Informatica - Universita di Torino Svizzera 185 - 10149 - Torino - Italy E-Mail liliana@ Abstract This paper presents a cooperative consultation system on a restricted domain. The system builds hypotheses on the user s plan and avoids misunderstandings with consequent repair dialogues through clarification dialogues in case of ambiguity. The role played by constraints in the generation of the answer is characterized in order to limit the cases of ambiguities requiring a clarification dialogue. The answers of the system are generated at different levels of detail according to the user s competence in the domain. INTRODUCTION This paper presents a plan-based consultation system for getting information on how to achieve a goal in a restricted The main purpose of tile system is to recognize the user s plans and goals to build cooperative answers in a flexible way Allen 83 Carberry 90 The system is composed of two parts hypotheses construction and response generation. The consưuction of hypotheses is based on Context Models CMs Carberry 90 Carberry uses default inferences Carberry 90b to select a single hypothesis for building the final answer of die system and in case the choice is incorrect a repair dialogue is started. Instead in our system we consider all plausible hypodieses and if die ambiguity among them is relevant for die generation of the response we try to solve it by starting a clarification dialogue. According to van Beek and Cohen 91 clarification dialogues are simpler for die user than repaữ ones because tiiey only involve yes no questions on die selected ambiguous plans. Furtiiermore repair dialogues generally require a stronger participation of the user. Finally if die misunderstanding is not discovered die system delivers information tiiat is not proper to the user s case. .