<?xml version="1.0" standalone="yes"?>
<Paper uid="C90-1017">
  <Title>STS: An Experimental Sentence Translation System</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> As a preliminary step towards the development of an on-line interactive system, we develop the STS system to establish whether our lexicalist translation model, using a GB-.inspired parser, lexical transfer and lexical projection, provides the kind of efficiency required for on-line translation 2. In its present implementation, STS translates sentences from French to English. It can handle a limited, although not trivial subset of clausal structures, using a lexical database of more than 5,000 entries (including compounds and idiomatic expressions).</Paragraph>
    <Paragraph position="1"> Accurate natural language translation requires a wide range of cognitive abilities, including grammatical knowledge of the languages involved but also some amount of extralinguistic knowledge and common sense reasoning. Lack of weUdefined theoretical models of knowledge and conmlon sense reasoning makes fully automatic high quality translation unlikely in the near future. null In the meantime, what appears to be an increasingly appealing alternative is on-line interactive machine translation, i.e. systems which can consult the user when they are unable to solve a problem 1. However, in order to be a viable alternative to other machine or machine-aided translation models, and in addition to the usual requirements of reasonable quality and low cost, an on-line interactive system must also satisfy the requirements of real-time systems and in particular be fast enough not to use the user's patience.</Paragraph>
    <Paragraph position="2"> *Part of the work described in this paper has been supported by a grant from the Swiss national science foundation (grant no 11-25362.88).</Paragraph>
    <Paragraph position="3"> 'For a discussion of on-line interactive translation see Kay (1982), Tomita (1986), Johnson and Whitelock (1987), among others.</Paragraph>
  </Section>
class="xml-element"></Paper>