<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-1061">
  <Title>Using Discourse Predictions for Ambiguity Resolution</Title>
  <Section position="2" start_page="0" end_page="358" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> A system which processes spoken language must address all of the ambiguities arising when processing written language, plus other ambiguities specitie to the speech processing task. These include ambiguities derived from speech disfluencies, speech recognition errors, and the lack of clearly marked sentence boundaries. Because a large flexible grammar is necessary to handle these features of spoken language, as a side-effect the number of ambiguities increases. In this paper, we discuss how we apply discourse predictions along with non context-based predictions to the problem of parse disambiguation. This work has been carried out in the context of Enthusiast, a Spanish-to-English speech-to-speech translation system (Woszcyna et al., 1993; Suhm et al., 1994; Levin et al., 1995), which currently translates spontaneous dialogues between two people trying to schedule a meeting time.</Paragraph>
    <Paragraph position="1"> A key feature of our approach is that it allows multiple hypotheses to be processed through the system in parallel, and uses context to disambiguate among alternatives in the linal stage of the process, where knowledge can be exploited to the fullest extent. In our system, numerical predictions based on the more local utterance level are generated by tile parser. The larger discourse context is processed and maintained by a plan-based discourse processor, which also produces context-based predictions for ambiguities. Our goal was to combine the predictions from the context-based discourse processing approach with those from the non context-based parser approach.</Paragraph>
    <Paragraph position="2"> In developing our discourse processor for disambiguation we needed to address three major issues. First, most plan-based or finite state automaton based discourse processors (Allen and Schubert, 1991; Smith, Hipp, and Biermann, 1995; Lambert, 1993; Reithinger and Maim:, 1995), including tile one we initially developed (l~.osd et al., 1995), only take one semantic representation as input at a time: thus, we had to extend the discourse processor so thai; it can handle multiple hypotheses as input. Secondly, we needed to quantify the disambiguating predictions made by the plan-based discourse processor in order to combine these predictions with the non context-based ones. Finally, we needed a method for combining context-based and non context-based predictions in such a way as to reflect not only which factors are important, but also to what extent they are important, and under what circumstances. We assume that knowledge from different sources provides different perspectives on the disambiguation task, each specializing in different types of ambiguities.</Paragraph>
    <Paragraph position="3"> In this paper, we concentrate on the first two issues which are imperative to integrate a traditional plan-based discourse processor into the disambiguation module of a whole system. The third issue is very important for successful confl)ination of predictions from different knowledge sources.</Paragraph>
    <Paragraph position="4"> We address this issue elsewhere in (Rosd and Qu, 1995).</Paragraph>
    <Paragraph position="5"> The paper is organized as follows: Fh'st, we briefly introduce the Enthusiast speech translation system and discuss the ambiguity problem in Enthusiast. Then we discuss our discourse processor, focusing on those characteristics needed to generate predictions lbr disambiguation. Finally, we evaluate our performance, and demonstrate that tile use of discourse context improves performance on disambiguation tasks over a purely non context-based approach in the absence of cumulative error.</Paragraph>
  </Section>
class="xml-element"></Paper>