<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1107">
  <Title>Probabilistic Sentence Reduction Using Support Vector Machines</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The most popular methods of sentence reduction for text summarization are corpus based methods. Jing (Jing 00) developed a method to remove extraneous phrases from sentences by using multiple sources of knowledge to decide which phrases could be removed. However, while this method exploits a simple model for sentence reduction by using statistics computed from a corpus, a better model can be obtained by using a learning approach.</Paragraph>
    <Paragraph position="1"> Knight and Marcu (Knight and Marcu 02) proposed a corpus based sentence reduction method using machine learning techniques.</Paragraph>
    <Paragraph position="2"> They discussed a noisy-channel based approach and a decision tree based approach to sentence reduction. Their algorithms provide the best way to scale up the full problem of sentence reduction using available data. However, these algorithms require that the word order of a given sentence and its reduced sentence are the same.</Paragraph>
    <Paragraph position="3"> Nguyen and Horiguchi (Nguyen and Horiguchi 03) presented a new sentence reduction technique based on a decision tree model without that constraint. They also indicated that semantic information is useful for sentence reduction tasks.</Paragraph>
    <Paragraph position="4"> The major drawback of previous works on sentence reduction is that those methods are likely to output local optimal results, which may have lower accuracy. This problem is caused by the inherent sentence reduction model; that is, only a single reduced sentence can be obtained.</Paragraph>
    <Paragraph position="5"> As pointed out by Lin (Lin 03), the best sentence reduction output for a single sentence is not approximately best for text summarization.</Paragraph>
    <Paragraph position="6"> This means that \local optimal&amp;quot; refers to the best reduced output for a single sentence, while the best reduced output for the whole text is \global optimal&amp;quot;. Thus, it would be very valuable if the sentence reduction task could generate multiple reduced outputs and select the best one using the whole text document. However, such a sentence reduction method has not yet been proposed.</Paragraph>
    <Paragraph position="7"> Support Vector Machines (Vapnik 95), on the other hand, are strong learning methods in comparison with decision tree learning and other learning methods (Sholkopf 97). The goal of this paper is to illustrate the potential of SVMs for enhancing the accuracy of sentence reduction in comparison with previous work. Accordingly, we describe a novel deterministic method for sentence reduction using SVMs and a two-stage method using pairwise coupling (Hastie 98). To solve the problem of generating multiple best outputs, we propose a probabilistic sentence reduction model, in which a variant of probabilistic SVMs using a two-stage method with pairwise coupling is discussed.</Paragraph>
    <Paragraph position="8"> The rest of this paper will be organized as follows: Section 2 introduces the Support Vector Machines learning. Section 3 describes the previous work on sentence reduction and our deterministic sentence reduction using SVMs.</Paragraph>
    <Paragraph position="9"> We also discuss remaining problems of deterministic sentence reduction. Section 4 presents a probabilistic sentence reduction method using support vector machines to solve this problem.</Paragraph>
    <Paragraph position="10"> Section 5 discusses implementation and our experimental results; Section 6 gives our conclusions and describes some problems that remain to be solved in the future.</Paragraph>
  </Section>
class="xml-element"></Paper>