<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-2013">
  <Title>Approaches to Zero Adnominal Recognition</Title>
  <Section position="2" start_page="0" end_page="2" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> (1) Zebras always need to watch out for lions.</Paragraph>
    <Paragraph position="1">  Therefore, even while eating grass, so that able to see behind, eyes are placed at face-side. This is a surface-level English translation of a naturally occurring &amp;quot;unambiguous&amp;quot; Japanese discourse. By &amp;quot;unambiguous,&amp;quot; we mean that Japanese speakers find no difficulty in interpreting this discourse segment, including whose eyes are being talked about. Moreover, Japanese speakers find this segment quite &amp;quot;coherent,&amp;quot; even though there seems to be no surface level indication of who is eating or seeing, or whose eyes are being mentioned in this four-clause discourse segment.</Paragraph>
    <Paragraph position="2">  However, this is not always the case with Japanese as a Second Language (JSL) learners.</Paragraph>
    <Paragraph position="3">  What constitutes &amp;quot;coherence&amp;quot; has been studied by many researchers. Reference is one of the linguistic devices that create textual unity, i.e., cohe- null This was verified by an informal poll conducted on 15 native speakers of Japanese.</Paragraph>
    <Paragraph position="4">  Personal communication with a JSL teacher.</Paragraph>
    <Paragraph position="5"> sion (Halliday and Hasan, 1976). Reference also contributes to the semantic continuity and content connectivity of a discourse, i.e., coherence. Coherence represents the natural and reasonable connections between utterances that make for easy understanding, and thus lower inferential load for hearers.</Paragraph>
    <Paragraph position="6"> The Japanese language uses ellipsis as its major type of referential expression. Certain elements are ellipted when they are recoverable from a given context or from relevant knowledge. These ellipses may include verbals and nominals; the missing nominals have been termed &amp;quot;zero pronouns,&amp;quot; &amp;quot;zero pronominals,&amp;quot; &amp;quot;zero arguments,&amp;quot; or simply &amp;quot;zeros&amp;quot; by researchers.</Paragraph>
    <Paragraph position="7"> How many zeros are contained in (1), for example, largely depends on how zeros are defined. In the literature, zeros are usually defined as elements recoverable from the valency requirements of the predicate with which they occur. However, does this cover all the zeros in Japanese? Does this explain all the content connectivity created by nominal ellipsis in Japanese? In this paper, we introduce a subgroup of zeros, what we call &amp;quot;zero adnominals,&amp;quot; in contrast to other well-recognized &amp;quot;zero arguments&amp;quot; and investigate possible approaches to recognizing these newly-defined zeros, in an attempt to incorporate them in an automatic zero detecting tool for JSL teachers that aims to promote effective instruction of zeros. In section 2, we provide the definition of zero adnominals, and present the results of their manual identification in the corpus. Section 3 describes the theoretical and pedagogical motivations for this study. Section 4 illustrates the syntactic/semantic classification of the zero adnominal examples found in the corpus. Based on the classification results, we propose lexical information-based heuristics, and present a preliminary evaluation. In the final two sections, we present related work, and discuss possible future directions.</Paragraph>
  </Section>
class="xml-element"></Paper>