<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1009">
  <Title>Discriminative Word Alignment with Conditional Random Fields</Title>
  <Section position="2" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> In this paper we present a novel approach for inducing word alignments from sentence aligned data. We use a Conditional Random Field (CRF), a discriminative model, which is estimated on a small supervised training set. The CRF is conditioned on both the source and target texts, and thus allows for the use of arbitrary and overlapping features over these data.</Paragraph>
    <Paragraph position="1"> Moreover, the CRF has efficient training and decoding processes which both find globally optimal solutions.</Paragraph>
    <Paragraph position="2"> We apply this alignment model to both French-English and Romanian-English language pairs. We show how a large number of highly predictive features can be easily incorporated into the CRF, and  demonstratethatevenwithonlyafewhundred word-aligned training sentences, our model improves over the current state-of-the-art with alignment error rates of 5.29 and 25.8 for the two tasks respectively.</Paragraph>
  </Section>
class="xml-element"></Paper>