<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0712">
  <Title>An Integrated Approach for Arabic-English Named Entity Translation</Title>
  <Section position="7" start_page="91" end_page="91" type="concl">
    <SectionTitle>
6 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> We have presented an integrated system that can handle various NE categories and requires the regular parallel and monolingual corpora which are typically used in the training of any statistical machine translation system along with NEs identifier.</Paragraph>
    <Paragraph position="1"> The proposed approach does not require any costly special resources, lexicons or any type of annotated data.</Paragraph>
    <Paragraph position="2"> The system is composed of multiple translation modules that give flexibility for different named entities type's translation requirements. This gives a great flexibility that enables the system to handle NEs of any type.</Paragraph>
    <Paragraph position="3"> We will evaluate the effect of the system on CLIR and MT tasks. We will also try to investigate new approaches for deploying NE translation in general phrase based MT system.</Paragraph>
  </Section>
class="xml-element"></Paper>