<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-1614">
  <Title>Urdu Localization Project: Lexicon, MT and TTS (ULP)</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In today's information age it is critical to provide access to information to people for their development. One precursor to this access is availability of information in the native languages.</Paragraph>
    <Paragraph position="1"> Due to limitations in technology, it has not been possible to generate information in many languages of the world. However, with recent advances in internationalization and localization technology, many languages are not enabled.</Paragraph>
    <Paragraph position="2"> However, as this is recent development, the published content in these languages is still limited, and far lags behind the content available for English, Spanish and some other languages spoken in developed countries. Realizing this gap in content and the need to provide access to information to its citizens, Government of Pakistan has recently launched Urdu Localization Project</Paragraph>
    <Paragraph position="4"> Urdu Localization Project is a three-year initiative being undertaken by Center for Research in Urdu Language Processing (www.crulp.org) and is funded This project will enable translation and access of English content to literate and illiterate Urdu speakers.</Paragraph>
    <Paragraph position="5"> Urdu Localization Project aims to provide access to existing English language content to Urdu language speakers. The project has three components: Urdu Computational Lexicon, English-to-Urdu Machine Translation System, Urdu Text-to-Speech system. This paper briefly describes the architecture and work achieved todate for different systems within ULP.</Paragraph>
  </Section>
class="xml-element"></Paper>