<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1097">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics Semi-Supervised Training for Statistical Word Alignment</Title>
  <Section position="2" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> We introduce a semi-supervised approach to training for statistical machine translation that alternates the traditional Expectation Maximization step that is applied on a large training corpus with a discriminative step aimed at increasing word-alignment quality on a small, manually word-aligned sub-corpus. We show that our algorithm leads not only to improved alignments but also to machine translation outputs of higher quality.</Paragraph>
  </Section>
class="xml-element"></Paper>