<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2112">
  <Title>Word Alignment for Languages with Scarce Resources Using Bilingual Corpora of Other Language Pairs</Title>
  <Section position="8" start_page="880" end_page="880" type="concl">
    <SectionTitle>
7 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> This paper presented a word alignment approach for languages with scarce resources using bilingual corpora of other language pairs. To perform word alignment between languages L1 and L2, we introduce a pivot language L3 and bilingual corpora in L1-L3 and L2-L3. Based on these two corpora and with the L3 as a pivot language, we proposed an approach to estimate the parameters of the statistical word alignment model. This approach can build a word alignment model for the desired language pair even if no bilingual corpus is available in this language pair. Experimental results indicate a relative error reduction of 10.41% as compared with the method using the small bilingual corpus.</Paragraph>
    <Paragraph position="1"> In addition, we interpolated the above model with the model trained on the small L1-L2 bilingual corpus to further improve word alignment between L1 and L2. This interpolated model further improved the word alignment results by achieving a relative error rate reduction of 12.51% as compared with the method using the two corpora in L1-L3 and L3-L2, and a relative error rate reduction of 21.30% as compared with the method using the small bilingual corpus in L1 and L2.</Paragraph>
    <Paragraph position="2"> In future work, we will perform more evaluations. First, we will further investigate the effect of the size of corpora on the alignment results.</Paragraph>
    <Paragraph position="3"> Second, we will investigate different parameter combination of the induced model and the original model. Third, we will also investigate how simpler IBM models 1 and 2 perform, in comparison with IBM models 3 and 4. Last, we will evaluate the word alignment results in a real machine translation system, to examine whether lower word alignment error rate will result in higher translation accuracy.</Paragraph>
  </Section>
class="xml-element"></Paper>