<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2077">
  <Title>Reinforcing English Countability Prediction with One Countability per Discourse Property</Title>
  <Section position="3" start_page="0" end_page="595" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Countability of English nouns is important in various natural language processing tasks. It is particularly important in machine translation from a source language that does not have an article system similar to that of English, such as Chinese and Japanese, into English since it determines the range of possible determiners including articles. It also plays an important role in determining whether a noun can take singular and plural forms.</Paragraph>
    <Paragraph position="1"> Another useful application is to detect errors in article usage and singular/plural usage in the writing of second language learners. Given countability, these errors can be detected in many cases. For example, an error can be detected from We have a furniture. given that the noun furniture is uncountable since uncountable nouns do not tolerate the inde nite article.</Paragraph>
    <Paragraph position="2"> Because of the wide range of applications, researchers have done a lot of work related to countability. Baldwin and Bond (2003a; 2003b) have proposed a method for automatically learning countability from corpus data. Lapata and Keller (2005) and Peng and Araki (2005) have proposed web-based models for learning countability. Others including Bond and Vatikiotis-Bateson (2002) and O'Hara et al. (2003) use ontology to determine countability.</Paragraph>
    <Paragraph position="3"> In the application to error detection, researchers have explored alternative approaches since sources of evidence for determining countability are limited compared to other applications. Articles and the singular/plural distinction, which are informative for countability, cannot be used in countability prediction aiming at detecting errors in article usage and singular/plural usage. Returning to the previous example, the countability of the noun furniture cannot be determined as uncountable by the inde nite article; rst, its countability has to be predicted without the inde nite article, and only then whether or not it tolerates the inde nite article is examined using the predicted countability. Also, unlike in machine translation, the source language is not given in the writing of second language learners such as essays, which means that information available is limited.</Paragraph>
    <Paragraph position="4"> To overcome these limitations, Nagata et al. (2005a) have proposed a method for predicting countability that relies solely on words (except articles and other determiners) surrounding the target noun. Nagata et al. (2005b) have shown that the method is effective to detecting errors in article usage and singular/plural usage in the writing of Japanese learners of English. They  also have shown that it is likely that performance of the error detection will improve as accuracy of the countability prediction increases since most of false positives are due to mispredictions.</Paragraph>
    <Paragraph position="5"> In this paper, we propose a method for reinforcing countability prediction by introducing a novel concept called one countability per discourse that is an extension of one sense per discourse proposed by Gale et al. (1992). It claims that when a noun appears more than once in a discourse, they will all share the same countability in the discourse. The basic idea of the proposed method is that initially mispredicted countability can be corrected using ef ciently the one countability per discourse property.</Paragraph>
    <Paragraph position="6"> The next section introduces the one countability per discourse concept and shows that it can be a good source of evidence for predicting countability. Section 3 discusses how it can be ef ciently exploited to predict countability. Section 4 describes the proposed method. Section 5 describes experiments conducted to evaluate the proposed method and discusses the results.</Paragraph>
  </Section>
class="xml-element"></Paper>