<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-1068">
  <Title>Context-dependent SMT Model using Bilingual Verb-Noun Collocation</Title>
  <Section position="19" start_page="555" end_page="555" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we proposed a new chunk-based statistical machine translation model that is tightly coupled with a language model. In order to alleviate the data sparseness in chunk-based translation, we applied the back-off translation method at the head-tail and morpheme levels. Moreover, in order to get more semantically plausible translation results by considering long-distance dependency, we utilized verb-noun collocations which were automatically extracted by using chunk alignment and a monolingual dependency parser. As a case study, we experimented on the language pair of Japanese and Korean. Experimental results showed that the proposed translation model is very effective in improving performance. The use of bilingual verb-noun collocations is also useful for improving the performance.</Paragraph>
    <Paragraph position="1"> However, we still have some problems of the data sparseness and the low coverage of bilingual verb-noun collocation. In the near future, we will try to solve the data sparseness problem and to increase the coverage and accuracy of verb-noun collocations.</Paragraph>
  </Section>
class="xml-element"></Paper>