<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-0504">
  <Title>An HMM Approach to Vowel Restoration in Arabic and Hebrew</Title>
  <Section position="9" start_page="0" end_page="0" type="concl">
    <SectionTitle>
8 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we demonstrated the use of a statistically based approach for vowel restoration in Semitic languages. We wish to demonstrate that HMMs are a useful tool for computational processing of Semitic languages, and that these models generalize to other languages. For the task of vocalizing the vowels according to their phonetic classification, the system we have proposed achieves an accuracy of 87% for Hebrew. For the task of restoring the exact vowel pattern, we achieved an accuracy of 81% for Hebrew texts and 86% for Arabic texts. Thus, we have shown that the contextual information gained by using HMMs is beneficial for this task.</Paragraph>
  </Section>
class="xml-element"></Paper>