<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2312">
  <Title>Resolution of Lexical Ambiguities in Spoken Dialogue Systems</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Following Ide and Veronis (1998) we can distinguish between data- and knowledge-driven word sense disambiguation (WSD). Given the basic distinction between written text and spoken utterances, we follow Allen et al. (2001) and differentiate further between controlled and conversational spoken dialogue systems. Neither data- nor knowledge-driven word sense disambiguation has been performed on speech data stemming from human interactions with dialogue systems, since multi-domain conversational spoken dialogue systems for human computer interaction (HCI) have not existed in the past. Now that speech data from multi-domain systems have become available, corresponding experiments and evaluations have become feasible.</Paragraph>
    <Paragraph position="1"> In this paper we present the results of first word sense disambiguation annotation experiments on data from spoken interactions with multi-domain dialogue systems. Additionally, we describe the results of a corresponding evaluation of a data- and a knowledge-driven word sense disambiguation system on that data. For knowledge-driven disambiguation we examined whether the ontology-based method for computing semantic coherence introduced by Gurevych et al. (2003a) can be employed to disambiguate between alternative interpretations, i.e. concept representations, of a given speech recognition hypothesis (SRH) at hand. We will show the results of its evaluation in the semantic interpretation task of WSD. For example, in speech recognition hypotheses containing forms of the German verb kommen, i.e. (to) come, a decision had to be made whether its meaning corresponds to the motion sense or to the showing sense, i.e. becoming mapped onto either a</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
MotionDirectedTransliteratedProcessor a
</SectionTitle>
      <Paragraph position="0"> WatchPerceptualProcess in the terminology of our spoken language understanding system. For a data-driven approach we employed a highly supervised learning algorithm introduced by Brants (2000) and trained it on a corpus of annotated data. A second set of semantically annotated speech recognition hypotheses was employed as a gold-standard for evaluating both the ontology-based and supervised learning method. Both data sets were annotated by separate human annotators.</Paragraph>
      <Paragraph position="1"> All annotated data stems from log files of an automatic speech recognition system that was implemented in the SMARTKOM system (Wahlster et al., 2001; Wahlster, 2003). It is important to point out that there are at least two essential differences between spontaneous speech WSD and textual WSD, i.e., a2 a smaller size of processable context as well as a2 imperfections, hesitations, disfluencies and speech recognition errors.</Paragraph>
      <Paragraph position="2"> Existing spoken language understanding systems, that are not shallow and thusly produce deep syntactic and semantic representations for multiple domains, e.g. the production system approach described by Engel (2002) or unification-based approaches described by Crysmann et al. (2002), have shown to be more suitable for well-formed input but less robust in case of imperfect input. For conversational and reliable dialogue systems that achieve satisfactory scores in evaluation frameworks such as proposed by Walker et al. (2000) or Beringer et al. (2002) for multi-modal dialogue systems, we need robust knowledge- or data-driven methods for disambiguating the sometimes less than ideal output of the large vocabulary spontaneous speech recognizers. In the long run, we would also like to avoid expensive pre-processing work, which is necessary for both ontology-driven and supervised learning methods, i.e. labor intensive ontology engineering and data annotation respectively. null</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>