<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1632">
  <Title>Using Linguistically Motivated Features for Paragraph Boundary Identification</Title>
  <Section position="3" start_page="0" end_page="267" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Our work is concerned with multi-document summarization, namely with the merging of multiple documents about the same topic taken from the web. We view summarization as extraction of important sentences from the text. As a consequence of the merging process the layout of the documents is lost. In order to create the layout of the output, the document structure (Power et al., 2003) has to be regenerated. One aspect of this structure is of particular importance for our work: the paragraph structure. In web documents paragraph boundaries are used to anchor figures and illustrations, so that the figures are always aligned with the same paragraph even when the font size or the window size is changed. Since we want to include figures in the generated summaries, paragraph segmentation is an important subtask in our application. null Besides multi-document summarization of web documents, paragraph boundary identification (PBI) could be useful for a number of different applications, such as producing the layout for transcripts provided by speech recognizers and optical character recognition systems, and determining the layout of documents generated for output devices with different screen size.</Paragraph>
    <Paragraph position="1"> Though related to the task of topic segmentation which stimulated a large number of studies (Hearst, 1997; Choi, 2000; Galley et al., 2003, inter alia), paragraph segmentation has not been thoroughly investigated so far. We explain this by the fact that paragraphs are considered a stylistic phenomenon and that there is no unanimous opinion on what the function of the paragraph is. Some authors (Irmscher (1972) as cited by Stark (1988)) suggest that paragraph structure is arbitrary and can not be determined based solely on the properties of the text. Still, psycholinguistic studies report that humans agree, at least to some extent, on placing boundaries between paragraphs. These studies also note that paragraph boundaries are informative and make the reader perceive paragraph-initial sentences as being important (Stark, 1988). In contrast to topic segmentation, paragraph segmentation has the advantage that large amounts of annotated data are readily availabe for supervised learning.</Paragraph>
    <Paragraph position="2"> In this paper we describe our approach to paragraph segmentation. Previous work (Sporleder &amp; Lapata, 2004; 2006) mainly focused on superficial and easily obtainable surface features like punctuation, quotes, distance and words in the sentence. Their approach was claimed to be domain- and language-independent. Our hypothesis, however, is that linguistically motivated features, which we compute automatically, provide a better paragraph segmentation than Sporleder &amp; Lapata's surface ones, though our approach may loose some of the  domain-independence. We test our hypothesis on a corpus of biographies downloaded from the German Wikipedia1. The results we report in this paper indicate that linguistically motivated features outperform surface features significantly. It turned out that pronominalization and information structure contribute to the determination of paragraph boundaries while discourse cues have a negative effect.</Paragraph>
    <Paragraph position="3"> The paper is organized as follows: First, we describe related work in Section 2, then in Section 3 our data is introduced. The baselines, the machine learners, the features and the experimental setup are given in Section 4. Section 5 reports and discusses the results.</Paragraph>
  </Section>
class="xml-element"></Paper>