<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2185">
  <Title>An Interactive Domain Independent Approach to Robust Dialogue Interpretation</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In this paper we discuss ROSE, an interactive approach to robust interpretation developed in the context of the JANUS speech-to-speech translation system (Lavie et al., 1996). Previous interactive approaches to robust interpretation have either required excessive amounts of interaction (Ros4 and Waibel, 1994), depended upon domain dependent repair rules (Vail Noord, 1996; Danieli and Gerbino, 1995), or relied on the minimum distance parsing approach (Hipp, 1992; Smith, 1992; Lehman, 1989) which has been shown to be intractable in a large-scale system (Ros6 and Lavie, 1997). In contrast, the ROSE approach operates efficiently without any hand-coded repair knowledge. An empirical evaluation demonstrates the efficacy of this domain independent approach. A further evaluation demonstrates that the ROSE approach combines easily with available domain knowledge in order to improve the quality of the interaction.</Paragraph>
    <Paragraph position="1"> The ROSE approach is based on a model of human communication between speakers of different languages with a small shared language base. Humans who share a very small language base are able to communicate when the need arises by simplifying their speech patterns and negotiating until they manage to transmit their ideas to one another (Hatch, 1983). As the speaker is speaking, the listener &amp;quot;casts his net&amp;quot; in order to catch those fragments of speech that are comprehensible to him, which he then attempts to fit together semantically.</Paragraph>
    <Paragraph position="2"> His subsequent negotiation with the speaker builds upon this partial understanding. Similarly, ROSE repairs extragramlnatical input in two phases. The first phase, Repair Hypothesis Formation, is responsible for assembling a set of hypotheses about the meaning of the ungrammatical utterance. In the second phase, Interaction with the User, the system generates a set of queries, negotiating with the speaker in order to narrow down to a single best meaning representation hypothesis.</Paragraph>
    <Paragraph position="3"> This approach was evaluated in the context of the JANUS multi-lingual machine translation system. First, the system obtains a meaning representation for a sentence uttered in the source language. Then the resulting meaning representation structure is mapped onto a sentence in the target language using GENKIT (Tomita and Nyberg, 1988) with a sentence level generation grammar. Currently, the translation system deals with the scheduling domain where two speakers attempt to schedule a meeting together over the phone. This paper focuses on the Interaction phase. Details about the Hypothesis Formation phase are found in (Ros6, 1997).</Paragraph>
  </Section>
class="xml-element"></Paper>