<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3119">
  <Title>Syntax Augmented Machine Translation via Chart Parsing</Title>
  <Section position="2" start_page="0" end_page="138" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Recent work in machine translation has evolved from the traditional word (Brown et al., 1993) and phrase based (Koehn et al., 2003a) models to include hierarchical phrase models (Chiang, 2005) and bilingual synchronous grammars (Melamed, 2004).</Paragraph>
    <Paragraph position="1"> These advances are motivated by the desire to integrate richer knowledge sources within the translation process with the explicit goal of producing more fluent translations in the target language. The hierarchical translation operations introduced in these methods call for extensions to the traditional beam decoder (Koehn et al., 2003a). In this work we introduce techniques to generate syntactically motivated generalized phrases and discuss issues in chart parser based decoding in the statistical machine translation environment.</Paragraph>
    <Paragraph position="2"> (Chiang, 2005) generates synchronous context-free grammar (SynCFG) rules from an existing phrase translation table. These rules can be viewed as phrase pairs with mixed lexical and non-terminal entries, where non-terminal entries (occurring as pairs in the source and target side) represent placeholders for inserting additional phrases pairs (which again may contain nonterminals) at decoding time.</Paragraph>
    <Paragraph position="3"> While (Chiang, 2005) uses only two nonterminal symbols in his grammar, we introduce multiple syntactic categories, taking advantage of a target language parser for this information. While (Yamada and Knight, 2002) represent syntactical information in the decoding process through a series of transformation operations, we operate directly at the phrase level. In addition to the benefits that come from a more structured hierarchical rule set, we believe that these restrictions serve as a syntax driven language model that can guide the decoding process, as n-gram context based language models do in traditional decoding. In the following sections, we describe our phrase annotation and generalization process followed by the design and pruning decisions in our chart parser. We give results on the French-English Europarl data and conclude with prospects for future work.</Paragraph>
  </Section>
class="xml-element"></Paper>