<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-2104">
  <Title>Learning Mechanism in Machine Translation System &amp;quot;PIVOT&amp;quot;</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1. Introduction
</SectionTitle>
    <Paragraph position="0"> In the current machine translation system, users cannot always get correct translated sentences at the first translation. This is due to the low ability of the grammar rules end low quality of the dictionarY.</Paragraph>
    <Paragraph position="1"> Woreover, the grealar rules and the dictionary need customization for each document of varying fields and contents. It is very difficult to prepare beforehand the information corresponding to various fields.</Paragraph>
    <Paragraph position="2"> NEC has developed a machine translation systea &amp;quot;PlV0T&amp;quot;(Jepanese to English/English to Japanese) as the translation support systea for business use. The translation part of PIVOT is the rule-based system and adopts the interlingue method. PIVOT provides a special editor so that the user can correct the analysis results. The user can interactively select suitable translation equivalents, can correct dependency, case (semantic relation), and so on. In technical manual documents which ere the main objects of machine translation, there ore many expressions that appear more than once. The analysis results of such expressions are often the sane. At present, PIVOT has learning functien for selection of translation equivalents, but it does not have such mechanism for dependency and case. The user has to correct many similar errors in dependency and case, so a heavy burden is laid on the user. Information give~ by the user can be regarded as customizing information for the document to be translated. Therefore, for o practical use system, it is an important issue to provide a framework to improve translation by using correction information froa the user.</Paragraph>
    <Paragraph position="3"> There are various approaches for analyzing seutences by using accumulated dependencies. One system automatically extracts all dependencies which have ne ambiguJty\[5\]. Another system accumulates only the dependencies which are directly corrected by the user \[2\]. In 8lure et al.\[4J, the s~stem accumulates all dependencies in the sentence that are corrected or confirmed by the user.</Paragraph>
    <Paragraph position="4"> There ere two ways for remembering the keys in the dependency structures to he accumulated: one by the spelling and the other by the semantic code. However, the rougb selantic code used in the current system does not have high distinguishing ability, end often causes bad influence. For example, consider the following sentences.</Paragraph>
    <Paragraph position="5"> lie looked at the singing man with opera glasses.</Paragraph>
    <Paragraph position="6"> lie looked at the man who is singing with the aicrophone. null The seaantie code &amp;quot;Instrument&amp;quot; is usually assigned to &amp;quot;~-~ C/~(opera glasses)&amp;quot; and &amp;quot;~4 ~ (microphone)&amp;quot;. Therefore, it ien't possible to fix dependence relation such as &amp;quot;~5(singing)&amp;quot; with &amp;quot;~4C/(microphone)&amp;quot;, and &amp;quot;.E~(look)&amp;quot; with &amp;quot;#&amp;quot;~P~X(opera glasses)&amp;quot;. In the process of using learning results there is an approach that adopts best matching by computing siailarity with accumulated inforaatioo\[i3. The example-based approach that translates by retrieving examples and calculating siailarity has been investigated. These systems also adept best aatching\[l\]\[6\]\[7\].</Paragraph>
    <Paragraph position="7"> This paper proposes an approach that can ilprove the translation quality b~ interactively accumulating dependency and case structures corrected by the user. In the learning process, the syntactle head, tile syntactic dependent, and the ease between them are stored in the association database. $o avoid side effects, head and dependent words are stored in the form of spellings.</Paragraph>
    <Paragraph position="8"> This makes it easier for the user to understand the behavior of the system. Four types of matching methods are examined that ere used in matching betgeen the possible analysis structures and the association datebase. null Section 2 describes analysis editing function in PIY0T/JE(dapanese to English). Section 3 explains the learning mechanism, and the results of simulation on actual manuals are presented in Section 4.</Paragraph>
  </Section>
class="xml-element"></Paper>