<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-2039">
  <Title>Unsupervised Induction of Modern Standard Arabic Verb Classes</Title>
  <Section position="2" start_page="0" end_page="1" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The creation of the Arabic Treebank (ATB) facilitates corpus based studies of many interesting linguistic phenomena in Modern Standard Arabic (MSA).</Paragraph>
    <Paragraph position="1">  The ATB comprises manually annotated morphological and syntactic analyses of newswire text from different Arabic sources. We exploit the ATB for the novel task of automatically creating lexical semantic verb classes for MSA. We are interested in the problem of classifying verbs in MSA into groups that share semantic elements of meaning as they exhibit similar syntactic behavior. This  http://www.ldc.org manner of classifying verbs in a language is mainly advocated by Levin (1993). The Levin Hypothesis (LH) contends that verbs that exhibit similar syntactic behavior share element(s) of meaning. There exists a relatively extensive classification of English verbs according to different syntactic alternations, and numerous linguistic studies of other languages illustrate that LH holds cross linguistically, in spite of variations in the verb class assignment (Guerssel et al., 1985).</Paragraph>
    <Paragraph position="2"> For MSA, the only test of LH has been the work of Mahmoud (1991), arguing for Middle and Unaccusative alternations in Arabic. To date, no general study of MSA verbs and alternations exists. We address this problem by automatically inducing such classes, exploiting explicit syntactic and morphological information in the ATB.</Paragraph>
    <Paragraph position="3"> Inducing such classes automatically allows for a large-scale study of different linguistic phenomena within the MSA verb system, as well as cross-linguistic comparison with their English counterparts. Moreover, drawing on generalizations yielded by such a classification could potentially be useful in several NLP problems such as Information Extraction, Event Detection, Information Retrieval and Word Sense Disambiguation, not to mention the facilitation of lexical resource creation such as MSA WordNets and ontologies.</Paragraph>
  </Section>
class="xml-element"></Paper>