<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1078">
  <Title>Chart-Based Transfer Rule Application in Machine Translation</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> ri~'ansfer-based Machine 'Kanslation systenls require a procedure for choosing the set of transtier rules for generating a target language I;ranslation from a given source language sentence.</Paragraph>
    <Paragraph position="1"> This procedure is trivial tbr a system if, given a (:ontext, one transtb.r rule. can l)e selected un~mfl)iguously. O|;herwise, choosing the besl; set; of transfer rules may involve the. evaluation of mmmrous competing sets. In fact, the number of l)ossible transfer rule combinations increases exponentially with the length of the source, language sentence,. This situation mirrors the t)roblem of choosing productions in a nondeterministic parser, in this paI)er, we descril)e a system for choosing transfer rules, based on statistical chart parsing (Bol)row, 1990; Chitrao and Grishman, 1990; Caraballo and Charniak, 1997; Charniak et al., 1998).</Paragraph>
    <Paragraph position="2"> In our Machine %'anslation system, transfer rules are generated automatically from parsed parallel text along the lines of (Matsulnoto el; al,, 1993; Meyers et al., 1996; Meyers et al., 1998b). Our system tends to acquire a large nmnber of transt~r rules, due lnainly to 3,1ternative ways of translating the same sequences of words, non-literal translations in parallel text and parsing e, rrors. It is therefore crucial that our system choose the best set of rules efficiently. While the technique discussed he.re obviously applies to similar such systems, it could also apply to hand-coded systems in which each word or group of words is related to more than one transfer rule. D)r example, both Multra (Hein, 1996) and the Eurotra system described in (Way el; al., 1997) require components for deciding which combination of transtbr rules to use. The proi).osed technique may 1)e used with syst;ems like these, t)rovided that all transfer rules are assigned initial scores rating thcqr at)propriateness for translation. These al)t)rol)riateness ratings couhl be dependent or independent of context.</Paragraph>
  </Section>
class="xml-element"></Paper>