<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1069">
  <Title>An IR Approach for Translating New Words from Nonparallel, Comparable Texts</Title>
  <Section position="7" start_page="418" end_page="418" type="evalu">
    <SectionTitle>
10 Discussions
</SectionTitle>
    <Paragraph position="0"> Our algorithm is the first to have generated a collocation bilingual lexicon, albeit small, from a nonparallel, comparable corpus. We have shown that the algorithm has good precision, but the recall is low due to the difficulty in extracting unambiguous Chinese and English words.</Paragraph>
    <Paragraph position="1"> Better results can be obtained when the following changes are made: * improve seed word lexicon reliability by stemming and POS tagging on both English and Chinese texts; * improve Chinese segmentation by using a larger monolingual Chinese lexicon; * use larger corpus to generate more unknown words and their candidates by statistical methods; We will test the precision and recall of the algorithm on a larger set of unknown words.</Paragraph>
  </Section>
class="xml-element"></Paper>