<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2031">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics Robust Word Sense Translation by EM Learning of Frame Semantics</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> As early as in the 1950s, semantic nets were invented as an &amp;quot;interlingua&amp;quot; for machine translation. null The &amp;quot;semantic net&amp;quot; or &amp;quot;semantic map&amp;quot; that humans possess in the cognitive process is a structure of concept classes and lexicon (Illes and Francis 1999). In addition, the frame-semantic representation of predicate-argument relations has gained much attention in the research community. The Berkeley FrameNet (Baker et al.</Paragraph>
    <Paragraph position="1"> 1998) is such an example.</Paragraph>
    <Paragraph position="2"> We suggest that in addition to dictionaries, bi-lingual frame semantics (word sense dictionary) is a useful resource for lexical selection in the translation process of a statistical machine translation system. Manual inspection of the contrastive error analysis data from a state-of-the-art SMT system showed that around 20% of the error sentences produced could have been avoided if the correct predicate argument information was used (Och et al. 2003). Therefore, frame semantics can provide another layer of translation disambiguation in these systems.</Paragraph>
    <Paragraph position="3"> We therefore propose to generate a bilingual frame semantics mapping (word sense dictionary), simulating the &amp;quot;semantic map&amp;quot; in a bilingual speaker. Other questions of interest to us include how concept classes in English and Chinese break down and map to each other.</Paragraph>
    <Paragraph position="4"> This paper is organized as follows. In section 2, we present the one-frame-two-languages idea of bilingual frame semantics representation. In section 3, we explain the EM algorithm for generating a bilingual ontology fully automatically.</Paragraph>
    <Paragraph position="5"> In section 4, we present an evaluation on word sense translation. Section 5 describes an evaluation on how well bilingual frame semantics can improve translation disambiguation. We then discuss related work in section 6, conclude in section 7, and finally discuss future work in section 8.</Paragraph>
  </Section>
class="xml-element"></Paper>