<?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="2" start_page="0" end_page="39" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> and that we are given the folh)wing Japanese input s(,~.tence (sl): (sl) watashi(l)ha de,,t~ku(cah'ulator) w,, shiy-OIISH rll.</Paragraph>
    <Paragraph position="1"> In the almve exami,h~s , (s l) in likely to Im more similar to (,,1) than (e2), b,~c~use the three Japanese verbs &amp;quot;kyouyotmuru~&amp;quot; &amp;quot;tsakan,&amp;quot; and &amp;quot;shiyousuru&amp;quot; are all w~ry simih~r, ~ and &amp;quot;dent~ku&amp;quot; (&amp;quot;calculator&amp;quot;) is more similar to &amp;quot;konl)yuutaa&amp;quot; (&amp;quot;computer&amp;quot;) than &amp;quot;kurum~'?' (&amp;quot;car&amp;quot;). If this is the case, the English output ohtained by using (el) is (tl),'-' whereas it should he 0,2): In recent years~ the example-based approach ha.s been used in many areas of natural language l)mcessing \[3, 7, 8, 10~ 9, 1\]. We haw~ been tlsing this al)proach to develop a transfer system called 5'imTra', \[13, 14, 16\]. However, a bottleneck occured in the collection of large numbers of translathm examples consisting of pairs of parsed structures in the source and target languages (hereafter we (:all these structures translation patterns)~ because parsing is not a perfi~et process. We now have some methods for overcoming this problem. For instance, recent studies \[2, 11, 6, 12\] have proposed mechanisms for collecting pairs of parsed structures automatically from translation examples, and in the previous paper \[15\], 1 proposed ,~ method for extracting relevant translation patterns by comparing a wrong translation resttlL and its correct translation. Using these methods, we ca.n now collect translation patterns reh~tively easily.</Paragraph>
    <Paragraph position="2"> There is, however, another problem ca.lled e~:ample inte,C/e,~nce, wl,ich means that an ,xceptional (or id iomatie) translation pattern is selected when a general translation pattern should be selected; this has t~ side-effect on the construction of a target structure.</Paragraph>
    <Paragraph position="3"> Suppose that we have the following two translation examples from Japanese to English (el) and (e2), (el) watashi(1) ha konpyuuta~(computer) wo kyouy-ollsllrll. null I share the use of ~ computer.</Paragraph>
    <Paragraph position="4"> (e2) watashi(I) ha~ kurum~(ear) wo tsnkau.</Paragraph>
    <Paragraph position="5"> \]&amp;quot; /ISe a. car.</Paragraph>
    <Paragraph position="6"> (tl) I use the use of a calculator.</Paragraph>
    <Paragraph position="7"> (t2) I use a calculator.</Paragraph>
    <Paragraph position="8"> This probh~nl occurs because examph'~-ba,sed transfer systems choose examples simply on the basis of similarity. This ca.n be considered by using the analogy of cells like those shown in Figure 1. In the \[igure, a dot represents a translation examl)le ~ and a cell represents a spac(! in which an input is determined to be similar. According to this analogy, all example-blused system chex:ks the cell in which an input is located, ;~nd uses an ex~mple gow~rning the cell. If a new exa.mt)le is added in this space, it cell for it is created as if cell division. If an input happens to fall into the cell of an exceptional example, it is wrongly tr~mslated. Ther,d'ore~ an exce.ptitmal example shoukl be added as ~ spechd cell (a shaded dot in Figure 1) that h~us no exte,t in the example-based space, so that it. cannot he used unless it matches the input exactly. Thus, an examl~le-based transfer system must deal with ,~xctq)tiomd translation patterns st:parately when calcuhtting similarity.</Paragraph>
    <Paragraph position="9"> This paper describes a mechanism used in Sim~lFan for dealing with exceptional translation patterns in the same framework as general translation patterns, and proposes a method for identifying exceptional tnrnsh~tion patterns in ~ tr~ulsla.tion pattern base.</Paragraph>
    <Paragraph position="10"> The next section describes a mechanism for dealing with such translatimL patter.s, and Section 3 de1 Actually, they are in the same c~ttegory (or the same lmff) in the JItpttll~!Se thestmrus lh nr i-Go-l\[you \[5\].</Paragraph>
    <Paragraph position="11"> r\['h\[~ Illltill Vftl'll iS /:llltllgl!C/l fl'tllll &amp;quot;shltrt!&amp;quot; to IU4t :&amp;quot; \]leCallSly &amp;quot;share&amp;quot; is not ~t transh~tiou of &amp;quot;shiyousuru.&amp;quot;  lation patterns. Some experiments are reported in Section 4, and some issues are discussed in Section 5.</Paragraph>
    <Paragraph position="12"> Finally, some concluding remarks bring this paper to an ond,</Paragraph>
  </Section>
class="xml-element"></Paper>