<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-0408">
  <Title>English-to-Mandarin Speech Translation with Head Transducers</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In this paper we describe the head transducer model used for translation in an experimental English-to-Mandarin speech translation system.</Paragraph>
    <Paragraph position="1"> Head transducer models consist of collections of weighted finite state transducers associated with pairs of lexical items in a bilingual lexicon. Head transducers operate &amp;quot;outwards&amp;quot; from the heads of phrases; they convert the left and right dependents of a source word into the left and right dependents of a corresponding target word.</Paragraph>
    <Paragraph position="2"> The transducer model can be characterized as a statistical translation model, but unlike the models proposed by Brown et al. (1990, 1993), these models have non-uniform linguistically motivated structure, at present coded by hand. The underlying linguistic structure of these models is similar to dependency grammar (Hudson 1984), although dependency representations are not explicitly constructed in our approach to translation. The original motivation for the head transducer models was  that they are simpler and more amenable to automatic model structure acquisition as compared with earlier transfer models.</Paragraph>
    <Paragraph position="3"> We first describe the head transduction approach in general in Section 2. In Section 3 we explain properties of the particular head transducers used in the experimental English-to-Mandarin speech translator. In Section 4, we explain how head transducers help satisfy the requirements of the speech translation application, and we conclude in Section 5.</Paragraph>
  </Section>
class="xml-element"></Paper>