<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-1005">
  <Title>Towards Machine \]ranslal; on U. inf C, onC(,xt, m,1 hfforma,tion</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 Introduction
</SectionTitle>
    <Paragraph position="0"> Current Machine qh'anslatiou (MT) systems proc,~ss input sentence by sentence. I\[owever, experience wil.h English and Japanese has shown that some languages difl'er to such a degree that sentential translation yiehls poor results, l,eL us first compare the results of a conventional MT sysl.em with those we expect, t,o  get for MT with context: t. J::q'lJf\]~-._-i~C/{:C//,?)\[ b v,-)-- 1/~3-'.~E~gfi PS&amp;quot; 2)i L v, K 2. K-7: ~t- laJaS'd?,l~ ~a ~t~.I;~y b t:: o 4. k-c g \];! ( 5'~ko  This might be translated by a current, machine tl'anslation system as shown in Figure 11: It can clearly l)e seen that meaning in IHally seI/tenees is obscured. Let us compare this with I.he resuits of a system using simple cont.exl.ual informal,ion ms shown in Figure 2: This secol/d translation is i-tlllch Ill(H'(? CO\]lO\['{~ll{. ;IH{I better preserves the meaning of the original se,lten{'o. An attempt has therefore I}een made to solve some of tile problems of translal.ing languages SllCIt sis Japanese and English using contextual information. Due to \[.he consideral.ions of wanting to produce a high quality small-sized MT system, lhe approach taken is to use tile resources awdlahle in an exisl;ing MT system and to process the contextu;d i,l\['orlmd.ion l There is obviously n great difference in results Imtweet, systems, hnl, l.hese translat.icms relweSent tyl}iCal {uHe, llted) r~.stdts fi'om a numher of systems, a) and I}) options,hq}end on the default settings of individual systems  1. The Chief I)evel{}pment li;ngineer develot}ed two new TV models and Four new video ,nodels last year.</Paragraph>
    <Paragraph position="1"> 2. a) A vi{h'o was shil)ped to the Sales Section.</Paragraph>
    <Paragraph position="2"> b) We/Soineone shil)pcd a video to the Sales Seel, ion.</Paragraph>
    <Paragraph position="3"> &amp;quot;I. a) 'l'wo models were released straight away. l}) \\/e/~olneone released I,wo models straight a*,v a.g.</Paragraph>
    <Paragraph position="4"> d. It sohl very well.</Paragraph>
    <Paragraph position="5"> Figure 1: (jonventional M'P Results I. The Chief l)evelolmmnt Engineer developed DA'O IICW 'FV lllodels ~llld \[()sir flew video n/oriels lasl year.</Paragraph>
    <Paragraph position="6"> 2. lie shipped the videos l.o t.he Sales Section. 3. They released two models straight away.</Paragraph>
    <Paragraph position="7"> 4. Tlmy sold very well.</Paragraph>
    <Paragraph position="8">  on a shallow level only, using the information gained to guide the translation on a &amp;quot;best guess&amp;quot; basis. This kiml of feal,ure with rat.her light; processing for the production of a higher quality translation is desirable in a pracl,ical MT system because the advanl.ages of large-scah~ processing for deep conl.extual ilfform;d.ioi, are likely to he limited in Lids apl~lical.ion.</Paragraph>
  </Section>
class="xml-element"></Paper>