<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-1074">
  <Title>Paraphrasing with Bilingual Parallel Corpora</Title>
  <Section position="2" start_page="0" end_page="597" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Paraphrases are alternative ways of conveying the same information. Paraphrases are useful in a number of NLP applications. In natural language generation the production of paraphrases allows for the creation of more varied and fluent text (Iordanskaja et al., 1991). In multidocument summarization the identification of paraphrases allows information repeated across documents to be condensed (McKeown et al., 2002). In the automatic evaluation of machine translation, paraphrases may help to alleviate problems presented by the fact that there are often alternative and equally valid ways of translating a text (Pang et al., 2003). In question answering, discovering paraphrased answers may provide additional evidence that an answer is correct (Ibrahim et al., 2003).</Paragraph>
    <Paragraph position="1"> In this paper we introduce a novel method for extracting paraphrases that uses bilingual parallel corpora. Past work (Barzilay and McKeown, 2001; Barzilay and Lee, 2003; Pang et al., 2003; Ibrahim et al., 2003) has examined the use of monolingual parallel corpora for paraphrase extraction. Examples of monolingual parallel corpora that have been used are multiple translations of classical French novels into English, and data created for machine translation evaluation methods such as Bleu (Papineni et al., 2002) which use multiple reference translations.</Paragraph>
    <Paragraph position="2"> While the results reported for these methods are impressive, their usefulness is limited by the scarcity of monolingual parallel corpora. Small data sets mean a limited number of paraphrases can be extracted. Furthermore, the narrow range of text genres available for monolingual parallel corpora limits the range of contexts in which the paraphrases can be used.</Paragraph>
    <Paragraph position="3"> Instead of relying on scarce monolingual parallel data, our method utilizes the abundance of bilingual parallel data that is available. This allows us to create a much larger inventory of phrases that is applicable to a wider range of texts.</Paragraph>
    <Paragraph position="4"> Our method for identifying paraphrases is an extension of recent work in phrase-based statistical machine translation (Koehn et al., 2003). The essence of our method is to align phrases in a bilingual parallel corpus, and equate different English phrases that are aligned with the same phrase in the other language. This assumption of similar mean- null Emma burst into tears and he tried to comfort her, saying things to make her smile.</Paragraph>
    <Paragraph position="5"> Emma cried, and he tried to console her, adorning his words with puns.</Paragraph>
    <Paragraph position="6"> Figure 1: Using a monolingal parallel corpus to extract paraphrases ing when multiple phrases map onto a single foreign language phrase is the converse of the assumption made in the word sense disambiguation work of Diab and Resnik (2002) which posits different word senses when a single English word maps onto different words in the foreign language (we return to this point in Section 4.4).</Paragraph>
    <Paragraph position="7"> The remainder of this paper is as follows: Section 2 contrasts our method for extracting paraphrases with the monolingual case, and describes how we rank the extracted paraphrases with a probability assignment. Section 3 describes our experimental setup and includes information about how phrases were selected, how we manually aligned parts of the bilingual corpus, and how we evaluated the paraphrases. Section 4 gives the results of our evaluation and gives a number of example paraphrases extracted with our technique. Section 5 reviews related work, and Section 6 discusses future directions.</Paragraph>
  </Section>
class="xml-element"></Paper>