<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-1011">
  <Title>Portable Knowledge Sources for Machine Translation</Title>
  <Section position="6" start_page="88" end_page="88" type="concl">
    <SectionTitle>
7. Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper, we have proposed it new machine trlcnslitton mechanism based on portable, kn(~wledge sonrees.</Paragraph>
    <Paragraph position="1"> It provides MT systems with an efficient way of acqulring ar,(l utilizing the vital inR~rmlttion from the nser in order to gradually achieve correct translation in at multi-domain, multi-user environment. Since the dOCllmen) lint (or a lint of previously translated documents) is usually read-only, it is not only a convenient unit for storing domain-oriented tlisamblguation knowledge, I,ut also an ideal resource for machine translation that can be shared by many nse.rs.</Paragraph>
    <Paragraph position="2"> We have started organizing our knowledge sources into a doculnellt list. The c)trrent doc.nlllei|ts consist of four IBM AS/400 computer IuanllalS with about, 2'2,000 sentences and a CAD manual with about 10,000 sentences. Currently only alma) 1,200 sentences have been translated by using our prototype MT system Shalt2\[tl\] and corrected by the use.r for knowlpdge atcqulsition. The PKS rules art.' therefore few and not ready for qnantitative analysis. Some interesting occnrrences of words, however~ have already been found.</Paragraph>
    <Paragraph position="3"> In one of the above, manuals, for example, the noun &amp;quot;part&amp;quot; was used in two different word senses: as a hard-ware comlmnent and ms an abstract lmrtion of a whole.</Paragraph>
    <Paragraph position="4"> 'Phe first usage of this noun, howew~r, seemed more re~ stricted: it was always modiIied by a prolmr noun. In one manual, the word &amp;quot;llne&amp;quot; wa.~ clearly acnd consistently used to mean a specific mw on the screen, while in another it wins always used to mean at geometric component. null The iuteraetion of PKS rules has not been discussed in this paper) although it is a very interesting topic.</Paragraph>
    <Paragraph position="5"> Suppose that PI(2 rnles can also inch)de the word senses for each word. It is not clear whether the word senses in the rules shonld be considered its conditional (valid only if the pair of mo/lilier and modifiee is present) or absolute (no matter what the modifier and mtnlitiee acre).</Paragraph>
    <Paragraph position="6"> Only the latter case is handled by the PK1, and the former cases could be the exceptions to the PK 1 rules.</Paragraph>
    <Paragraph position="7"> If the &amp;quot;one sense per doenment&amp;quot; assnmption see)as too strong~ we can modify the PK1 aud 1'I;3 rules by adding contextual dependency to the rules so that at word sense or a word translation is valid only if the word appears with a certain modifier or modifiee, has at certain syntactic role~ and st) on.</Paragraph>
  </Section>
class="xml-element"></Paper>