<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1048">
  <Title>Generating Discourse Structures for Written Texts</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Many recent studies in Natural Language Processing have paid attention to Rhetorical Structure Theory (RST) (Mann and Thompson 1988; Hovy 1993; Marcu 2000; Forbes et al. 2003), a method of structured description of text. Although rhetorical structure has been found to be useful in many fields of text processing (Rutledge et al.</Paragraph>
    <Paragraph position="1"> 2000; Torrance and Bouayad-Agha 2001), only a few algorithms for implementing discourse analyzers have been proposed so far. Most research in this field concentrates on specific discourse phenomena (Schiffrin 1987; Litman and Hirschberg 1990). The amount of research available in discourse segmentation is considered small; in discourse parsing it is even smaller.</Paragraph>
    <Paragraph position="2"> The difficulties in developing a discourse parser are (i) recognizing discourse relations between text spans and (ii) deriving discourse structures from these relations. Marcu (2000)'s parser is based on cue phrases, and therefore faces problems when cue phrases are not present in the text. This system can apply to unrestricted texts, but faces combinatorial explosion. The disadvantage of Marcu's approach is that it produces a great number of trees during its process, which is the essential redundancy in computation. As the number of relations increases, the number of possible discourse trees increases exponentially. null Forbes et al. (2003) have a different approach of implementing a discourse parser for a Lexicalized Tree Adjoining Grammar (LTAG). They simplify discourse analysis by developing a grammar that uses cue phrases as anchors to connect discourse trees. Despite the potential of this approach for discourse analysis, the case of no cue phrase present in the text has not been fully investigated in their research. Polanyi et al.</Paragraph>
    <Paragraph position="3"> (2004) propose a far more complicated discourse system than that of Forbes et al. (2003) , which uses syntactic, semantic and lexical rules. Polanyi et al. have proved that their approach can provide promising results, especially in text summarization. null In this paper, different factors were investigated to achieve a better discourse parser, including syntactic information, constraints about textual adjacency and textual organization. With a given text and its syntactic information, the search space in which well-structured discourse trees of a text are produced is minimized.</Paragraph>
    <Paragraph position="4"> The rest of this paper is organized as follows.</Paragraph>
    <Paragraph position="5"> The discourse analyzer at the sentence-level is presented in Section 2. A detailed description of our text-level discourse parser is given in Section 3. In Section 4, we describe our experiments and discuss the results we have achieved so far. Section 5 concludes the paper and proposes possible future work on this approach.</Paragraph>
  </Section>
class="xml-element"></Paper>