<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1009">
  <Title>Discriminative Word Alignment with Conditional Random Fields</Title>
  <Section position="9" start_page="71" end_page="71" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have presented a novel approach for inducing word alignments from sentence aligned data.</Paragraph>
    <Paragraph position="1"> We showed how conditional random fields could be used for word alignment. These models allow for the use of arbitrary and overlapping features over the source and target sentences, making the most of small supervised training sets. Moreover, we showed how the CRF's inference and estimation methods allowed for efficient processing without sacrificing optimality, improving on previous heuristic based approaches.</Paragraph>
    <Paragraph position="2"> On both French-English and Romanian-English we showed that many highly predictive features can be easily incorporated into the CRF, and demonstrated that with only a few hundred word-aligned training sentences, our model outperforms thegenerativeModel4baseline. Whennofeatures are extracted from the sentence aligned corpus our model still achieves a low error rate. Furthermore, when we employ features derived from Model 4 alignments our CRF model achieves the highest reported results on both data sets.</Paragraph>
  </Section>
class="xml-element"></Paper>