<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0817">
  <Title>Combined word alignments</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> We briefly describe a word alignment system that combines two different methods in bitext correspondences identification. The first one is a hypotheses testing approach (Gale and Church, 1991; Melamed, 2001; Tufis 2002) while the second one is closer to a model estimating approach (Brown et al., 1993; Och and Ney, 2000). We show that combining the two aligners the results are significantly improved as compared to each individual aligner.</Paragraph>
    <Paragraph position="1"> Introduction In (Tufis, 2002) we described a translation equivalence extraction program called TREQ the development of which was twofold motivated: to help enriching the synsets of the Romanian wordnet (Tufis et al. 2004a) with new literals based on bilingual corpora evidence and to check the interlingual alignment of our wordnet against the Princeton Wordnet. The translation equivalence extractor has been also incorporated into a WSD system (Tufis et al., 2004b) part of a semantic web annotation platform. It also constituted the backbone of our TREQ-AL word aligner which successfully participated in the previous HLT-NAACL</Paragraph>
  </Section>
class="xml-element"></Paper>