Contextualizing Reflective Dialogue in a Spoken Conversational Tutor
Heather Pon-Barry
Center for the Study of Language and Information, Stanford University, 210 Panama Street, Stanford, CA 94305, USA, Tel: +1 650 725 2317, ponbarry@csli.stanford.edu
Brady Clark
Center for the Study of Language and Information, Stanford University, 210 Panama Street, Stanford, CA 94305, USA, bzack@csli.stanford.edu
Karl Schultz
Center for the Study of Language and Information, Stanford University, 210 Panama Street, Stanford, CA 94305, USA, schultzk@csli.stanford.edu
Elizabeth Owen Bratt
Center for the Study of Language and Information, Stanford University, 210 Panama Street, Stanford, CA 94305, USA, ebratt@csli.stanford.edu
Stanley Peters
Center for the Study of Language and Information, Stanford University, 210 Panama Street, Stanford, CA 94305, USA, peters@csli.stanford.edu
David Haley
Center for the Study of Language and Information, Stanford University, 210 Panama Street, Stanford, CA 94305, USA, dhaley@csli.stanford.edu
ABSTRACT: In this paper we describe the ways that SCoT, a Spoken Conversational Tutor, uses flexible and adaptive planning as well as multimodal task modeling to support the contextualization of learning in reflective dialogues. Past research on human tutoring has shown reflective discussions (discussions occurring after problem-solving) to be effective in helping students reason about their own actions (Katz, Allbritton & Connelly, 2003). However, presenting information in an understandable manner while leading a reflective discussion is difficult and without contextualization it is easy to confuse and frustrate students. This raises the question: how should intelligent tutoring systems effectively contextualize learning in a reflective discussion? We believe that multimodal task modeling, carried out by a flexible and adaptive planning agent, can facilitate this process of contextualization and lead to a more successful dialogue.
Keywords: Intelligent tutoring systems, Spoken dialogue, Reflective tutoring, Multimodality, Speech technology
[387 Kb]