<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2124">
  <Title>BiTAM: Bilingual Topic AdMixture Models for Word Alignment</Title>
  <Section position="8" start_page="975" end_page="975" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we proposed novel formalism for statistical word alignment based on bilingual admixture (BiTAM) models. Three BiTAM models were proposed and evaluated on word alignment and translation qualities against state-of-the-art translation models. The proposed models significantly improve the alignment accuracy and lead to better translation qualities. Incorporation of within-sentence dependencies such as the alignment-jumps and distortions, and a better treatment of the source monolingual model worth further investigations.</Paragraph>
  </Section>
class="xml-element"></Paper>