<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-1003">
  <Title>A Method for Distinguishing Exceptional and G(m(.~L1 .... Examples-' ~ in Example-based Tr~msfer Systems</Title>
  <Section position="6" start_page="40" end_page="42" type="evalu">
    <SectionTitle>
5 Discussion
</SectionTitle>
    <Paragraph position="0"> In conventhmal tra, nsfl,~r systems \[4\], transfer rules are roughly divhled into general ones and exceptional (or idiomatic) ones. The transfer system checks the excepth)nal ca.ses first, and if they cannot match the input then the system applies general rules. On the other hand, example-based transfer systems deal with translation patterns (or examples) uniformly on the basis of similarity, according to the example-b~sed pri,ciph,. 'rids m~ci,mism causes the exanlple interference problem. A very useful property of the example-I)~u~e(l approach is that it allows a sente.nce to be added as an examph~ if it cannot be dealt with properly. This holds if the same input :~s the newly added example is given~ but when the resolution of the slmilarity calculation is not enough, an input that is similar to but not exactly the same as the added example may not be dealt with properly, because there may be another similar example that is exceptional.</Paragraph>
    <Paragraph position="1"> 'l'hereh)re, it is very important to identify whether an example is general or exceptional.</Paragraph>
    <Paragraph position="2"> After application of the alg&lt;&gt;rithm described in this paper, translation patterns are classified into the fol-.</Paragraph>
    <Paragraph position="3"> lowing categories: general, exceptional (extra- and intra-), and neutral. Neutlal translation patterns, which are not ml~rke.d general or exceptional, are  translation patterns that do not h~ve sld~&gt;effects.</Paragraph>
    <Paragraph position="4"> They are n(~t used for a wide variety of words in the current translation p~tttern bmse. If m~)re translation patterns are added later, they m~ty be identified as general or exceptional. By this method, mm can enable the system to identify exceptional translation patterns automatically hy adding some general translation I&gt;atterns similar to them. This is a very useful feature for bootstrapping of ~t transh~ti&lt;m pattern base. A weak point of this algorithm, }mwever, is that it requires a large number of translation patterns. If enough translatiml patterns ;~re not given, exceptional translation l)atterns might n(,t be identi tie(\[, tlowever, collecting many tr;ulslatinn patterns is no longer a serious l)roblern, since several methods for eolleeti,ig them automatically have been pr/q)(Ised in recent studies \[2, 11, 14, 6\].</Paragraph>
    <Paragraph position="5"> The method proposed in this paper probad)ly does not comply with human intuition regarding idiomatic translation patterns; rather, it detects transh~timt patterns that are idiomatic for the system, in other words, patterns that might have side-effects in the current set of translati(m patte.rns. It prnl,ahly requires deeper scm~mtle pr()cessing to ide.nti fy transhttion patterns tlu~t are idiomt~tie in the conventional Sellse.</Paragraph>
  </Section>
class="xml-element"></Paper>