<?xml version="1.0" standalone="yes"?>
<Paper uid="N03-1030">
  <Title>Sentence Level Discourse Parsing using Syntactic and Lexical Information</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> By exploiting information encoded in human-produced syntactic trees (Marcus et al., 1993), research on probabilistic models of syntax has driven the performance of syntactic parsers to about 90% accuracy (Charniak, 2000; Collins, 2000). The absence of semantic and discourse annotated corpora prevented similar developments in semantic/discourse parsing. Fortunately, recent annotation projects have taken signi cant steps towards developing semantic (Fillmore et al., 2002; Kingsbury and Palmer, 2002) and discourse (Carlson et al., 2003) annotated corpora. Some of these annotation efforts have already had a computational impact. For example, Gildea and Jurafsky (2002) developed statistical models for automatically inducing semantic roles. In this paper, we describe probabilistic models and algorithms that exploit the discourseannotated corpus produced by Carlson et al. (2003).</Paragraph>
    <Paragraph position="1"> A discourse structure is a tree whose leaves correspond to elementary discourse units (edu)s, and whose internal nodes correspond to contiguous text spans (called discourse spans). An example of a discourse structure is the tree given in Figure 1. Each internal node in a discourse tree is characterized by a rhetorical relation, such it will use its network  as ATTRIBUTION and ENABLEMENT. Within a rhetorical relation a discourse span is also labeled as either NUCLEUS or SATELLITE. The distinction between nuclei and satellites comes from the empirical observation that a nucleus expresses what is more essential to the writer's purpose than a satellite. Discourse trees can be represented graphically in the style shown in Figure 1. The arrows link the satellite to the nucleus of a rhetorical relation. Arrows are labeled with the name of the rhetorical relation that holds between the linked units. Horizontal lines correspond to text spans, and vertical lines identify text spans which are nuclei.</Paragraph>
    <Paragraph position="2"> In this paper, we introduce two probabilistic models that can be used to identify elementary discourse units and build sentence-level discourse parse trees. We show how syntactic and lexical information can be exploited in the process of identifying elementary units of discourse and building sentence-level discourse trees. Our evaluation indicates that the discourse parsing model we propose is sophisticated enough to achieve near-human levels of performance on the task of deriving sentence-level discourse trees, when working with human-produced syntactic trees and discourse segments.</Paragraph>
  </Section>
class="xml-element"></Paper>