<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1052">
  <Title>Using an Ontology to Determine English Countability</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In English, nouns heading noun phrases are typically either countable or uncountable (also called count and mass). Countable nouns can be modi ed by denumerators, prototypically numbers, and have a morphologically marked plural form: one dog, two dogs. Uncountable nouns cannot be modi ed by denumerators, but can be modi ed by unspeci c quanti ers such as much, and do not show any number distinction (prototypically being singular): * one equipment, some equipment, *two equipments.</Paragraph>
    <Paragraph position="1"> Knowledge of countability is important when translating from a source language without obligatory number and countability distinctions to a target language that does make number distinctions. Some examples are Japanese-to-English (Ehara and Tanaka, 1993; Bond, 2001), Japanese-to-German (Siegel, 1996), and Chinese-to-English.</Paragraph>
    <Paragraph position="2"> For a system generating English, it is important to know the countability of the head noun, as this determines whether it can become plural, and the range of possible determiners. Knowledge of countability is particularly important in machine translation, because the closest trans-This research was done while the second author was visiting the NTT Communication Science Laboratories lation equivalent may have di erent countability from the source noun. Many languages, such as Chinese and Japanese, do not mark countability, which means that the choice of countability will be largely the responsibility of the generation component.</Paragraph>
    <Paragraph position="3"> In this paper, we measure how well semantic classes predict countability. Obviously, the answer depends both on how many countability distinctions are made, and how many semantic classes are used. If every sense of every word belongs to its own semantic class, then semantic classes will uniquely, although not usefully, predict countability. This is e ectively the position taken by Wierzbicka (1988), where the semantics of a noun, given in the Natural Semantic Metalanguage, always provides enough information to predict the countability. On the other hand, if there are only a handful of semantic classes, then they will have little predictive power. We rst de ne countability, and discuss its semantic motivation (x 2). Then we present the lexical resources used in our experiment (x 3), including the ontology of 2,710 semantic classes. Next, we describe the experiment, which uses the semantic classes of words in a Japanese-to-English transfer dictionary to predict their countability (x 4). Finally, we present the results and discuss the theoretical and practical implications in (x 5).</Paragraph>
  </Section>
class="xml-element"></Paper>