<?xml version="1.0" standalone="yes"?>
<Paper uid="H91-1025">
  <Title>A Statistical Approach to Sense Disambiguation in Machine Translation</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> An a,lluring a,spect of the staMstica,1 a,pproa,ch to ins,chine tra,nsla,tion rejuvena.ted by Brown, et al., \[_1\] is the systems.tic framework it provides for a.tta.cking the problem of lexicM dis~tmbigua.tion. For example, the system they describe tra,ns\]a.tes th.e French sentence Je vais prendre la ddeision a,s \[ will make the decision, thereby correctly interpreting prendre a.s make, The staMstica.l tra.nslation model, which supplies English. tra,nsla,tions of French words, prefers the more common tra.nslation take, but the trigram la.ngu.age mode\] recognizes tha.t the three-word sequence make the decision is much more proba\])le tha.n take the decision.</Paragraph>
    <Paragraph position="1"> The system is not a.lwa,ys so successful. It incorrectly renders Je vats prendre ma propre ddcision a.s 1 will take my own decision. Here, the la.nguage model does not realize tha, t take my own decision is improbable beca,use take a,nd decision no longer fall within a. single trigram.</Paragraph>
    <Paragraph position="2"> Errors such a.s this a,re common because otlr sta,tistical models o.ly capture loca,l phenomena,; if l, he context necessa,ry to determine ~ transla, tion fa,lls outside the scope of our models, the word is likely to be tra,nsla,ted incorrectly. However, if the re\]evant co.text is encoded locally, the word should be tra, nsla, ted correctly. We ca,n a,chieve this within the traditionM p,~radigm of a.na,lysis - tra,nsfer - synthesis by incorpora,ting into the ana,lysis pha,se a, sense--disa, mbigu~tion compo,ent that assigns sense la, bels to French words.</Paragraph>
    <Paragraph position="3"> \]if prendre is labeled with one sense in the context of ddcisiou but wil.h a, different sense in other contexts, then the tra,nsla,tion model will learn from training data tha,t the first sense usua,lly tra.nslates to make, where.a,s the other sense usua,lly tra.nslates to take.</Paragraph>
    <Paragraph position="4"> In this paper, we describe a. sta, tistica,1 procedure for constructing a. sense-disambiguation eomponent that label words so as to elucida.te their translations.</Paragraph>
  </Section>
class="xml-element"></Paper>