<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1090">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics A Clustered Global Phrase Reordering Model for Statistical Machine Translation</Title>
  <Section position="3" start_page="0" end_page="713" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Global reordering is essential to the translation of languages with different word orders. Ideally, a model should allow the reordering of any distance, because if we are to translate from Japanese to English, the verb in the Japanese sentence must be moved from the end of the sentence to the beginning just after the subject in the English sentence. a1 Graduated in March 2006 Standard phrase-based translation systems use a word distance-based reordering model in which non-monotonic phrase alignment is penalized based on the word distance between successively translated source phrases without considering the orientation of the phrase alignment or the identities of the source and target phrases (Koehn et al., 2003; Och and Ney, 2004). (Tillmann and Zhang, 2005) introduced the notion of a block (a pair of source and target phrases that are translations of each other), and proposed the block orientation bigram in which the local reordering of adjacent blocks are expressed as a three-valued orientation, namely Right (monotone), Left (swapped), or Neutral. A block with neutral orientation is supposed to be less strongly linked to its predecessor block: thus in their model, the global reordering is not explicitly modeled.</Paragraph>
    <Paragraph position="1"> In this paper, we present a global reordering model that explicitly models long distance reordering1. It predicts four type of reordering patterns, namely MA (monotone adjacent), MG (monotone gap), RA (reverse adjacent), and RG (reverse gap). There are based on the identities of the source and target phrases currently being translated, and the previously translated source and target phrases. The parameters of the reordering model are estimated from the phrase alignments of training bilingual sentences. To cope with sparseness, we use N-best phrase alignments and bilingual phrase clustering.</Paragraph>
    <Paragraph position="2"> In the following sections, we first describe the global phrase reordering model and its param1It might be misleading to call our reordering model &amp;quot;global&amp;quot; since it is at most considers two phrases. A truly global reordering model would take the entire sentence structure into account.</Paragraph>
    <Paragraph position="3">  eter estimation method including N-best phrase alignments and bilingual phrase clustering. Next, through an experiment, we show that the global phrase reordering model significantly improves the translation accuracy of the IWSLT-2005 Japanese-English translation task (Eck and Hori, 2005).</Paragraph>
  </Section>
class="xml-element"></Paper>