<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-0506">
  <Title>Building a Shallow Arabic Morphological Analyzer in One Day</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 Background
</SectionTitle>
    <Paragraph position="0"> Significant work has been done in the area of the Arabic morphological analysis. The three main approaches to the problem are: 1. The Symbolic Approach: In this approach, morphotactic (rules governing the combination of morphemes, which are meaning bearing units in the language) and orthographic (spelling rules) rules are programmed into a finite state transducer (FST). Koskenniemi proposed a two-level system for language morphology, which led to Antworth's two-level morphology system PC-KIMMO [9] [19]. Later, Beesley and Buckwalter developed an Arabic morphology system, ALPNET, that uses a slightly enhanced implementation of PC-KIMMO [10]. Currently, ALPNET is owned by Xerox and uses Xerox Finite-State Morphology tools [11]. However, this approach was criticized by Ahmed [8] for requiring excessive manual processing to state rules in an FST and for the ability only to analyze words that appear in Arabic dictionaries. Kiraz summarized many variations of the FST approach [12]. Much information on two-level morphology and PC-Kimmo is available in the PC-KIMMO user's guide [20].</Paragraph>
  </Section>
class="xml-element"></Paper>