<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2120">
  <Title>Stochastic Discourse Modeling in Spoken Dialogue Systems Using Semantic Dependency Graphs</Title>
  <Section position="3" start_page="0" end_page="937" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> It is a very tremendous vision of the computer technology to communicate with the machine using spoken language (Huang et al., 2001; Allen at al., 2001). Understanding of spontaneous language is arguably the core technology of the spoken dialogue systems, since the more accurate information obtained by the machine (Higashinaka et al., 2004), the more possibility to finish the dialogue task.</Paragraph>
    <Paragraph position="1"> Practical use of speech act theories in spoken language processing (Stolcke et al. 2000; Walker and Passonneau 2001; Wu et al., 2004) have given both insight and deeper understanding of verbal communication. Therefore, when considering the whole discourse, the relationship between the speech acts of the dialogue turns becomes extremely important. In the last decade, several practicable dialogue systems (McTEAR, 2002), such as air travel information service system, weather forecast system, automatic banking system, automatic train timetable information system, and the Circuit-Fix-it shop system, have been developed to extract the user's semantic entities using the semantic frames/slots and conceptual graphs. The dialogue management in these systems is able to handle the dialogue flow efficaciously. However, it is not applicable to the more complex applications such as &amp;quot;Type 5: the natural language conversational applications&amp;quot; defined by IBM (Rajesh and Linda, 2004). In Type 5 dialog systems, it is possible for the users to switch directly from one ongoing task to another. In the traditional approaches, the absence of precise speech act identification without discourse analysis will result in the failure in task switching. The capability for identifying the speech act and extracting the semantic objects by reasoning plays a more important role for the dialog systems. This research proposes a semantic dependency-based discourse model to capture and share the semantic objects among tasks that switch during a dialog for semantic resolution. Besides  acoustic speech recognition, natural language understanding is one of the most important research issues, since understanding and application restriction on the small scope is related to the data structures that are used to capture and store the meaningful items. Wang et al. (Wang et al., 2003) applied the object-oriented concept to provide a new semantic representation including semantic class and the learning algorithm for the combination of context free grammar and N-gram.</Paragraph>
    <Paragraph position="2"> Among these approaches, there are two essential issues about dialogue management in natural language processing. The first one is how to obtain the semantic object from the user's utterances. The second is a more effective speech act identification approach for semantic understanding is needed.</Paragraph>
    <Paragraph position="3"> Since speech act plays an important role in the development of dialogue management for dealing with complex applications, speech act identification with semantic interpretation will be the most important topic with respect to the methods used to control the dialogue with the users. This paper proposes an approach integrating semantic dependency graph and history/discourse information to model the dialogue discourse (Kudo and Matsumoto, 2000; Hacioglu et al., 2003; Gao and Suzuki, 2003). Three major components, such as semantic relation, semantic class and semantic role are adopted in the semantic dependency graph (Gildea and Jurasfky, 2002; Hacioglu and Ward, 2003). The semantic relations constrain the word sense and provide the method for disambiguation.</Paragraph>
    <Paragraph position="4"> Semantic roles are assigned when the relation established among semantic objects. Both semantic relations and roles are defined in many knowledge resources or ontologies, such as FrameNet (Baker et al., 2004) and HowNet with 65,000 concepts in Chinese and close to 75,000 English equivalents, is a bilingual knowledge-base describing relations between concepts and relations between the attributes of concepts with ontological view (Dong and Dong 2006). Generally speaking, semantic class is defined as a set with the elements that are usually the words with the same semantic interpretation.</Paragraph>
    <Paragraph position="5"> Hypernyms that are superordinate concepts of the words are usually used as the semantic classes just like the Hypernyms of synsets in WordNet (http://www.cogsci.princeton.edu/~wn/) or definitions of words' primary features in HowNet. Besides, the approach for understanding tries to find the implicit semantic dependency between the concepts and the dependency structure between concepts in the utterance are also taken into consideration. Instead of semantic frame/slot, semantic dependency graph can keep more information for dialogue understanding.</Paragraph>
  </Section>
class="xml-element"></Paper>