<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1407">
  <Title>Naruaki Masuno ++</Title>
  <Section position="3" start_page="0" end_page="1" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Textual expressions that (roughly) convey the same meaning are called paraphrases. Since generating and recognizing paraphrases has a potential to contribute to a broad range of natural language applications, such as MT,IE, and QA,many researchers have done a lot of practices on automatic paraphrasing in the last decade.</Paragraph>
    <Paragraph position="1"> Most previous studies have addressed paraphrase phenomena where the syntactic category is not changed: e.g., noun-to-noun (&amp;quot;document&amp;quot; =&amp;quot;article&amp;quot;), verb-to-verb (&amp;quot;raise&amp;quot;=&amp;quot;bring up&amp;quot;). In these inner-categorial paraphrasing, only limited types of problems arise when replacing words or phrases with their synonymous expressions.</Paragraph>
    <Paragraph position="2"> On the other hand, this paper focuses on inter-categorial paraphrasing, such as adjective-to-verb (&amp;quot;attractive&amp;quot; = &amp;quot;attract&amp;quot;) that leads to novel type of problems due to the prominent differences in meaning and usage. In other words, calculating those differences is more crucial to determine how they can or cannot be paraphrased.</Paragraph>
    <Paragraph position="3"> The aim of this study is to clarify what lexical knowledge is required for capturing those differences, and to explore where such a knowledge can be obtained from. Recent work in lexical semantics has shown that syntactic behaviors and semantic properties of words provide useful information to explain the mechanisms of several classes of paraphrases. More specifically, lexical properties involved in the theory of Lexical Conceptual Structure (LCS) (Jackendoff, 1990) have seemed to be beneficial because each verb does not function idiosyncratically. However, in the literature, there have been less studies for other syntactic categories than verbs. To the best of our knowledge, the Meaning-Text Theory (MTT) (Mel'Vcuk and Polgu`ere, 1987) is one of the very few frameworks. In MTT, lexical properties and inter-categorial paraphrasing are realized with a unique semantic representation irrespective of syntactic categories and what are called lexical functions, e.g., S  (receive)=reception.</Paragraph>
    <Paragraph position="4"> To make out how the recent advances in lexical semantics for verbs can be extended to other syntactic categories, we assess LCS for inter-categorial paraphrasing. We choose adjectives as a counterpart of paraphrasing because they behave relatively similar to verbs compared with other categories: both adjectives and verbs have inflection and function as predicates, adnominal elements, etc. Yet, we speculate that their difference in meaning and usage reveal intriguing generation problems. To put it briefly, adjective-to-verb paraphrasing in Japanese requires verbal suffixes such as &amp;quot;ta (past / attributive)&amp;quot; in example (1)  : (1) s. furui otera-no jushoku-o tazune-ta.</Paragraph>
    <Paragraph position="5"> be old temple-GEN priest-ACC to visit-PAST I visited a priest in the old temple.</Paragraph>
    <Paragraph position="6"> t. furubi-ta otera-no jushoku-o tazune-ta.</Paragraph>
    <Paragraph position="7"> to olden-ATTR temple-GEN priest-ACC to visit-PAST I visited a priest in the olden(ed) temple.</Paragraph>
  </Section>
class="xml-element"></Paper>