<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-1023">
  <Title>Classifiers in Japanese-to-English Machine Translation</Title>
  <Section position="7" start_page="128" end_page="129" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this im,l)er we pres,:ull; a,n analysis off (:lassitieT~, suii;al)le for use ill a .\]apanese-to-ldnglish ma&lt;:hin&lt;~ I, ranslal;ion sysl,('m. We divide (:lassitiers into four ma,ior tyl)es: UNIT, METI/.IC~ (~l/.()Ul) /Hid SI)},',CII,;S.</Paragraph>
    <Paragraph position="1"> IJNIT classifiers arc, further divided inl;o (IIqNEI{.AI,~ TYI'ICAI, ;I,II(l SI'E(:IAI,, whil(; METI{IC (;\]assitiers are divided iltl;o MEASUI/.I,; all(\[ CONTAINEI{ (:\]ilssifters. The analysis ix 1)ased on &lt;:ha.ra.&lt;:lx~risl;i(:s 1)e&lt;'uliar 1;o Japanese mM English, a.s well as i,h(', differences bel;we(m I;hem. The resuli;ing amtlysis ix shown {;&lt;&gt; }&gt;e similar t;o ()n(~ pr()pose(t tbr Thai, an unrelaJ;(xl laJtguage, suggesl:iug thai, it may I)e more widely al)pli(:al)le.</Paragraph>
    <Paragraph position="2"> The az|Mysis has }&gt;e(!n imt)lemen(x~d in NTT's ,/at)a.nes&lt;&gt;lx)-English machine (,ranslal;ion syst;(;m AL'.r-J/E si~&lt;:(,. 19.()4.11; makes 1)ossible a uniform an(l st;raigh(;forwa.rd l;re~-tt, m(:nL of n()un phrases headed t)y classifiers.</Paragraph>
    <Paragraph position="3"> Furl;h('J&amp;quot; work remains 1;() be done in (',xmnining the &lt;listribul;ion of classifiers in differ(;nt, domains, and possibly identit~ying classifiers a.ul,omal;i&lt;:a,lly.</Paragraph>
  </Section>
class="xml-element"></Paper>