<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-1811">
  <Title>A Disambiguation Method for Japanese Compound Verbs</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The treatment of multiword expressions (MWEs) has attracted much interest as an important issue (Sag et al. 2002). Japanese has diverse types of MWEs and there are difficulties in processing them (Baldwin and Bond 2002). In those studies, MWEs are defined as a &amp;quot;word with spaces&amp;quot; in English and &amp;quot;idiosyncratic interpretations that cross word boundaries&amp;quot; in Japanese. Verb particles as one type of MWE in English have been studied (Villavicencio and Copestake 2002). We predict that verb particles in English and compound verbs in Japanese have commonalities in terms of ambiguity and semantic constraints. For example, the English particle &amp;quot;up&amp;quot; has both an aspectual (&amp;quot;finish up writing&amp;quot; cf.</Paragraph>
    <Paragraph position="1"> &amp;quot;kaki-owaru&amp;quot;) and a spatial meaning (&amp;quot;go up the stairs&amp;quot; cf. &amp;quot;kake-agaru&amp;quot;), which is equivalent to the second verb in Japanese compound verbs. We investigate Japanese compound verbs (JCVs) and extract semantic constraints for the purpose of applying them to machine translation.</Paragraph>
    <Paragraph position="2"> JCVs consist of two verbs, the first verb (V1) and the second verb (V2). V1 always appears in the continuative form. In this paper, we discuss only &amp;quot;Verb-Verb&amp;quot; JCVs, which are a composition of two native Japanese verbs, for example oshi-ageru &amp;quot;push up&amp;quot;, tabe-sugiru &amp;quot;eat too much&amp;quot; and so on. JCVs of V1-V2 form are frequently used for expressing complex motion, elaborated phenomena and emotional state. However, JCVs have high productivity, a great number of ambiguities and semantic constraints between each constituent.</Paragraph>
    <Paragraph position="3"> Examples of correlation between semantic constraint and ambiguities of JCVs are given in (1).</Paragraph>
    <Paragraph position="4"> (1) a. nage-ageru &amp;quot;throw up&amp;quot;, keri-ageru &amp;quot;kick up&amp;quot;, mochi-ageru &amp;quot;lift up&amp;quot;, oshi-ageru &amp;quot;push up&amp;quot; b. yude-ageru &amp;quot;finish boiling&amp;quot;, mushi-ageru &amp;quot;finish steaming&amp;quot;, yaki-ageru &amp;quot;finish baking&amp;quot; Ageru &amp;quot;lift&amp;quot; has multiple meanings when it appears in the V2 position of a JCV. A directional compound verb in (1a) is formed by compounding ageru &amp;quot;lift&amp;quot; as V2 with a verb of motion like nageru &amp;quot;throw&amp;quot; and keru &amp;quot;kick&amp;quot; as V1. Conversely, an aspectual compound verb in (1b) is formed by combining ageru &amp;quot;lift&amp;quot; as V2 with a verb of cooking process like yuderu &amp;quot;boil&amp;quot; and musu &amp;quot;steam&amp;quot; as V1. There are a small number of such ambiguous verbs which appear as V2. Ambiguous JCVs are generated by compounding various instances of V1 with an ambiguous V2, which makes it difficult to process on computer.</Paragraph>
    <Paragraph position="5"> The analysis of JCVs has been discussed in the field of linguistics and natural language processing.</Paragraph>
    <Paragraph position="6"> In linguistics, JCVs have been studied mainly in terms of syntax (Kageyama 1999) and constraints on semantic structures (Matsumoto 1996, 1998).</Paragraph>
    <Paragraph position="7"> Himeno (2000) made a semantic analysis concerning the types of V2s which have multiple meanings. She classified JCVs by the meaning of their V2. However, she confounded the meaning of V1 with that of V2 in her classification. In order to clarify the semantic constraints between V1 and V2, we need to analyze each constituent individually.</Paragraph>
    <Paragraph position="8"> In natural language processing, Shirai (1998) proposed a method of building valency patterns for JCVs by compiling a Japanese and English corpus.</Paragraph>
    <Paragraph position="9"> This approach, in which whole compound verbs are registered in an electronic dictionary, can improve the translation rate of the system. However, it is inefficient to register all the compound verbs in advance. For that reason, it is desirable to develop a framework for understanding JCVs by processing each constituent.</Paragraph>
    <Paragraph position="10"> Based on this background, we propose a method employing rules which utilize semantic features and syntactic information to clarify the semantic constraints for disambiguation of JCVs.</Paragraph>
    <Paragraph position="11"> In this paper, we take two steps in order to construct a disambiguation method. The first step is to identify the meaning of V1 using by rules which an MT system or other lexical database should have already. The second step is to classify JCVs into semantic clusters and extract commonalities of semantic features on V1 (semantic information) and verb complements (syntactic information). We build rules using this obtained semantic and syntactic information. This is the major innovation of this study. The proposed method based on disambiguation rules has the advantage of being able to analyze new compound verbs not in the dictionary.</Paragraph>
    <Paragraph position="12"> Since the semantic restrictions of JCVs are similar to those of phrasal verbs in English (Villavicencio and Copestake 2002), there might be a possibility of applying our method to machine translation.</Paragraph>
    <Paragraph position="13"> The rest of the paper is structured as follows.</Paragraph>
    <Paragraph position="14"> Section 2 describes the definition, ambiguities and semantic relations of JCVs. Section 3 shows analysis results. The semantic analysis method is explained in Section 4. The evaluation of this method is discussed in Section 5. The conclusion of our study and implication for future work are stated at the end.</Paragraph>
  </Section>
class="xml-element"></Paper>