tailieunhanh - Báo cáo khoa học: "Data-oriented Monologue-to-Dialogue Generation"

This short paper introduces an implemented and evaluated monolingual Text-to-Text generation system. The system takes monologue and transforms it to two-participant dialogue. After briefly motivating the task of monologue-to-dialogue generation, we describe the system and present an evaluation in terms of fluency and accuracy. | Data-oriented Monologue-to-Dialogue Generation Paul Piwek Svetlana Stoyanchev Centre for Research in Computing Centre for Research in Computing The Open University The Open University Walton Hall Milton Keynes UK Walton Hall Milton Keynes UK Abstract This short paper introduces an implemented and evaluated monolingual Text-to-Text generation system. The system takes monologue and transforms it to two-participant dialogue. After briefly motivating the task of monologue-to-dialogue generation we describe the system and present an evaluation in terms of fluency and accuracy. 1 Introduction Several empirical studies show that delivering information in the form of a dialogue as opposed to monologue can be particularly effective for education Craig et al. 2000 Lee et al. 1998 and persuasion Suzuki and Yamada 2004 . Informationdelivering or expository dialogue was already employed by Plato to communicate his philosophy. It is used primarily to convey information and possibly also make an argument this in contrast with dramatic dialogue which focuses on character development and narrative. Expository dialogue lends itself well for presentation through computer-animated agents Prendinger and Ishizuka 2004 . Most information is however locked up as text in leaflets books newspapers etc. Automatic generation of dialogue from text in monologue makes it possible to convert information into dialogue as and when needed. This paper describes the first data-oriented monologue-to-dialogue generation system which relies on the automatic mapping of the discourse relations underlying monologue to appropriate se 242 quences of dialogue acts. The approach is data-oriented in that the mapping rules have been automatically derived from an annotated parallel mono-logue dialogue corpus rather than being handcrafted. The paper proceeds as follows. Section 2 reviews existing approaches to dialogue generation. Section 3 describes the current approach.