<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0826">
  <Title>Combining Linguistic Data Views for Phrase-based SMT</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> We describe the Spanish-to-English LDV-COMBO system for the Shared Task 2: &amp;quot;Exploiting Parallel Texts for Statistical Machine Translation&amp;quot; of the ACL-2005 Workshop on &amp;quot;Building and Using Parallel Texts: Data-Driven Machine Translation and Beyond&amp;quot;. Our approach explores the possibility of working with alignments at different levels of abstraction, using different degrees of linguistic annotation. Several phrase-based translation models are built out from these alignments. Their combination significatively outperforms any of them in isolation. Moreover, we have built a word-based translation model based on Word-Net which is used for unknown words.</Paragraph>
  </Section>
class="xml-element"></Paper>