<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1049">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics A Bottom-up Approach to Sentence Ordering for Multi-document Summarization</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Multi-document summarization (MDS) (Radev and McKeown, 1999) tackles the information overload problem by providing a condensed version of a set of documents. Among a number of sub-tasks involved in MDS, eg, sentence extraction, topic detection, sentence ordering, information extraction, sentence generation, etc., most MDS systems have been based on an extraction method, which identifies important textual segments (eg, sentences or paragraphs) in source documents. It is important for such MDS systems to determine a coherent arrangement of the textual segments extracted from multi-documents in order to reconstruct the text structure for summarization. Ordering information is also essential for [?]Research Fellow of the Japan Society for the Promotion of Science (JSPS) other text-generation applications such as Question Answering.</Paragraph>
    <Paragraph position="1"> A summary with improperly ordered sentences confuses the reader and degrades the quality/reliability of the summary itself. Barzilay (2002) has provided empirical evidence that proper order of extracted sentences improves their readability significantly. However, ordering a set of sentences into a coherent text is a non-trivial task. For example, identifying rhetorical relations (Mann and Thompson, 1988) in an ordered text has been a difficult task for computers, whereas our task is even more complicated: to reconstruct such relations from unordered sets of sentences. Source documents for a summary may have been written by different authors, by different writing styles, on different dates, and based on different background knowledge. We cannot expect that a set of extracted sentences from such diverse documents will be coherent on their own.</Paragraph>
    <Paragraph position="2"> Several strategies to determine sentence ordering have been proposed as described in section 2. However, the appropriate way to combine these strategies to achieve more coherent summaries remains unsolved. In this paper, we propose four criteria to capture the association of sentences in the context of multi-document summarization for newspaper articles. These criteria are integrated into one criterion by a supervised learning approach. We also propose a bottom-up approach in arranging sentences, which repeatedly concatenates textual segments until the overall segment with all sentences arranged, is achieved.</Paragraph>
  </Section>
class="xml-element"></Paper>