<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-2106">
  <Title>A System of Verbal Semantic Attributes Focused on the Syntactic Correspondence between Japanese and English</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1. Introduction
</SectionTitle>
    <Paragraph position="0"> Various machine translation systems have approached the stage of being put to practical use. However, the quality of the finished translation is not satisfactory in any of these systems. This is due to difficulties in limiting linguistic phenomena that are handled by machine translation systems. In particular, the analysis of linguistic expressions such as ellipsis and anaphoric references, which require contextual analysis, is imperfect. To introduce constraints brought about by context requires an enormous volume of knowledge of word meanings that can be used to determine the semantic relationships between one sentence and another.</Paragraph>
    <Paragraph position="1"> To avoid an explosion in the volume of knowledge, a technique is proposed for classifying word meanings and determining the relationships between words or between sentences using the typical attribute values of each word. Particularly in the case of context processing, the verbal semantic attributes that become the key factors in analyzing the flow of sentences constitute important knowledge.</Paragraph>
    <Paragraph position="2"> Various efforts have been made in researching verb classification. Muraki (1985) suggested a method for grouping Japanese verbs using their word meanings and their syntactic features. Tomiura et al. (1986) proposed a method for representing the meaning of verbs divided into fundamental meanings and reasoning rules. Ogino et al. (1989; EDR 1990) proposed a method for verb classification based on relations between verbs and co-occurring elements. Various efforts have been made to classify English verbs. For example, Levin (1993) proposed a method for the classification of 3000 English verbs that uses the relationship between syntactic behavior and shared meaning.</Paragraph>
    <Paragraph position="3"> The research about verb classification still tends to be limited solely to classification of the semantics of verbs per se. It does not take into account the relationship between word meanings and their usage within sentences and is not aimed at natural language processing. Thus, the full benefits that could be achieved in the analysis of tracking semantic relationships between sentences and eliminating the polyscmy of verbs have not been realized.</Paragraph>
    <Paragraph position="4"> This paper tbcusses on the relationship between word meanings of verbs and their usage, and seeks to classify the semantic attributes of verbs. These semantic attributes are used in defining the method of use of each verb in Japanese to English transfer pattern dictionaries. They furnish the key to tracing the semantic relationships of verbs that are used in a text.</Paragraph>
  </Section>
class="xml-element"></Paper>