<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1010">
  <Title>A Morphological Analyzer for Akkadian Verbal Forms with a Model of Phonetic Transformations</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Akkadian is a dead Semitic language that was spoken and written in Mesopotamia between 2800 and 0 B.C. The main difficulty in this language is that verbs take a great variety of forms that differ not only by their ending, as in Indo-European languages, but also by the beginning and by the middle part. The only constant in all the forms of a verb is the root, which is composed of three consonants. These consonants appear mixed with other consonants and various vowels. Furthermore, some of the root consonants may be &amp;quot;weak,&amp;quot; meaning they do not appear in actual forms. At times, a weak consonant simply disappears, at others, it mutates to another consonant or to a vowel.</Paragraph>
    <Paragraph position="1"> We have constructed a two-part morphological analyzer for Akkadian verbal forms. The first is a grammar, which describes the systematic morphotactics of Akkadian verbs. There is a single paradigm for all verbs, weak or strong.</Paragraph>
    <Paragraph position="2"> The second component is a transducer, which changes a given theoretical form generated by the grammar into an actual form, by applying some phonetic transformation rules (e.g., assimilation, mutation, etc.). This transducer does not rely on a phonetic theory but on a set of observed transformations. In fact, the transducer is primarily used backwards, to retrieve the theoretical original form from an actual word to be parsed.</Paragraph>
    <Paragraph position="3"> The morphological analyzer recognizes all the verbal forms we have collected so far. On the other hand, the second level is not efficient on long forms. The paper describes the first results obtained in a work in progress. These results show that more sophisticated computational methods must be used in order to improve the efficiency.</Paragraph>
    <Paragraph position="4"> The next section is devoted to the Akkadian language. It is followed by brief description of Akkadian verbs and how they conjugate. The morphological analyzer, its two components, and its results are presented in section 4.</Paragraph>
  </Section>
class="xml-element"></Paper>