<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0709">
  <Title>The Impact of Morphological Stemming on Arabic Mention Detection and Coreference Resolution</Title>
  <Section position="3" start_page="0" end_page="63" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Information extraction is a crucial step toward understanding and processing language. One goal of information extraction tasks is to identify important conceptual information in a discourse. These tasks have applications in summarization, information retrieval (one can get all hits for Washington/person and not the ones for Washington/state or Washington/city), data mining, question answering, language understanding, etc.</Paragraph>
    <Paragraph position="1"> In this paper we focus on the Entity Detection and Recognition task (EDR) for Arabic as described in ACE 2004 framework (ACE, 2004). The EDR has close ties to the named entity recognition (NER) and coreference resolution tasks, which have been the focus of several recent investigations (Bikel et al., 1997; Miller et al., 1998; Borthwick, 1999; Mikheev et al., 1999; Soon et al., 2001; Ng and Cardie, 2002; Florian et al., 2004), and have been at the center of evaluations such as: MUC-6, MUC-7, and the CoNLL'02 and CoNLL'03 shared tasks. Usually, in computational linguistics literature, a named entity is an instance of a location, a person, or an organization, and the NER task consists of identifying each of these occurrences. Instead, we will adopt the nomenclature of the Automatic Content Extraction program (NIST, 2004): we will call the instances of textual references to objects/abstractions mentions, which can be either named (e.g. John Mayor), nominal (the president) or pronominal (she, it). An entity is the aggregate of all the mentions (of any level) which refer to one conceptual entity. For instance, in the sentence President John Smith said he has no comments null there are two mentions (named and pronomial) but only one entity, formed by the set fJohn Smith, heg.</Paragraph>
    <Paragraph position="2"> We separate the EDR task into two parts: a mention detection step, which identifies and classifies all the mentions in a text - and a coreference resolution step, which combinines the detected mentions into groups that refer to the same object. In its entirety, the EDR task is arguably harder than traditional named entity recognition, because of the additional complexity involved in extracting non-named mentions (nominal and pronominal) and the requirement of grouping mentions into entities. This is particularly true for Arabic where nominals and pronouns are also attached to the word they modify. In fact, most Arabic words are morphologically derived from a list of base forms or stems, to which prefixes and suffixes can be attached to form Arabic surface forms (blank-delimited words). In addition to the different forms of the Arabic word that result from the  derivational and inflectional process, most prepositions, conjunctions, pronouns, and possessive forms are attached to the Arabic surface word. It is these orthographic variations and complex morphological structure that make Arabic language processing challenging (Xu et al., 2001; Xu et al., 2002).</Paragraph>
    <Paragraph position="3"> Both tasks are performed with a statistical framework: the mention detection system is similar to the one presented in (Florian et al., 2004) and the coreference resolution system is similar to the one described in (Luo et al., 2004). Both systems are built around from the maximum-entropy technique (Berger et al., 1996). We formulate the mention detection task as a sequence classification problem. While this approach is language independent, it must be modified to accomodate the particulars of the Arabic language. The Arabic words may be composed of zero or more prefixes, followed by a stem and zero or more suffixes. We begin with a segmentation of the written text before starting the classification. This segmentation process consists of separating the normal whitespace delimited words into (hypothesized) prefixes, stems, and suffixes, which become the subject of analysis (tokens). The resulting granularity of breaking words into prefixes and suffixes allows different mention type labels beyond the stem label (for instance, in the case of nominal and pronominal mentions). Additionally, because the prefixes and suffixes are quite frequent, directly processing unsegmented words results in significant data sparseness. We present in Section 2 the relevant particularities of the Arabic language for natural language processing, especially for the EDR task. We then describe the segmentation system we employed for this task in Section 3. Section 4 briefly describes our mention detection system, explaining the different feature types we use. We focus in particular on the stem n-gram, prefix n-gram, and suffix n-gram features that are specific to a morphologically rich language such as Arabic. We describe in Section 5 our coreference resolution system where we also describe the advantage of using stem based features. Section 6 shows and discusses the different experimental results and Section 7 concludes the paper.</Paragraph>
  </Section>
class="xml-element"></Paper>