<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0102">
  <Title>Teaching Dialogue to Interdisciplinary Teams through Toolkits</Title>
  <Section position="3" start_page="0" end_page="9" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Hands-on interaction with dialogue systems is a necessary component of a course on computational linguistics and natural language technology. And yet, it is clearly impracticable to have students in a quarterlong or semester-long course build a dialogue system from scratch. For this reason, instructors of these courses have experimented with various options to allow students to view the code of a working dialogue system, tweak code, or build their own application using a dialogue system toolkit. Some popular options include the NLTK (Loper and Bird, 2002), CSLU (Cole, 1999), Trindi (Larsson and Traum, 2000) and Regulus (Rayner et al., 2003) toolkits. However, each of these options has turned out to have disadvantages. Some of the toolkits require too much knowledge of linguistics for the average computer science student, and vice-versa, others require too much programming for the average linguist. What is needed is an extensible dialogue toolkit that allows easy application building for beginning students, and more sophisticated access to, and tweakability of, the models of discourse for advanced students.</Paragraph>
    <Paragraph position="1"> In addition, as computational linguists become increasingly interested in the role of non-verbal behavior in discourse and dialogue, more of us would like to give our students exposure to models of the interaction between language and nonverbal behaviors such as eye gaze, head nods and hand gestures. However, the available dialogue system toolkits either have no graphical body or if they do have (part of) a body--as in the case of the CSLU toolkit--the toolkit does not allow the implementation of alternative models of body-language interaction.</Paragraph>
    <Paragraph position="2"> We feel, therefore, that there is a need for a toolkit that allows the beginning graduate student-who may have some computer science or some linguistics background, but not both--to implement a working embodied dialogue system, as a way to experiment with models of discourse, dialogue, collaborative conversation and the interaction between verbal and nonverbal behavior in conversation. We believe the community as a whole must be engaged in the design, implementation and fielding of this kind of educational software. In this paper, we survey the experience that has led us to these conclusions and frame the broader discussion we hope the TNLP workshop will help to further.</Paragraph>
  </Section>
class="xml-element"></Paper>