<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-0316">
  <Title>POS-Tagger for English-Vietnamese Bilingual Corpus</Title>
  <Section position="5" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have just presented the POS-tagging for an automatically word-aligned English-Vietnamese parallel corpus by POS-tagging English words first and then projecting them to Vietnamese side later.</Paragraph>
    <Paragraph position="1"> The English POS-tagging is done in 2 steps: The basic tagging step is achieved through the available POS-tagger (Brown) and the correction step is achieved through the TBL learning method in which the information on the corresponding Vietnamese is used through available word-alignment in the EVC.</Paragraph>
    <Paragraph position="2"> The result of POS-tagging of Vietnamese in the English-Vietnamese bilingual corpus plays a meaningful role in the building of the automatic training corpus for the Vietnamese processors in need of parts of speech (such as Vietnamese POS-taggers, Vietnamese parser, etc.). By making use of the language typology' s differences and the word-alignments in bilingual corpus for the mutual disambiguation, we are still able to improve the result of the English POS-tagging of the currently powerful English POS-taggers.</Paragraph>
    <Paragraph position="3"> Currently, we are improving the speed of training period by using Fast TBL algorithm instead of TBL one.</Paragraph>
    <Paragraph position="4"> In the future, we will improve this serial POS-tagging to the parallel POS-tagging for both English and Vietnamese simultaneously after we obtain the exact Vietnamese POS-tags in the parallel corpus of SUSANNE.</Paragraph>
  </Section>
class="xml-element"></Paper>