<?xml version="1.0" standalone="yes"?>
<Paper uid="X96-1026">
  <Title>CHINESE INFORMATION EXTRACTION AND RETRIEVAL</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1. BACKGROUND
</SectionTitle>
    <Paragraph position="0"> As a reinvention laboratory, the TIPSTER Program offers the Government not only an opportunity to foster large scale research and development, but also avenues to deploy the resulting enhanced technologies. The primary focus of TIPSTER Phase One was to advance the state-of-the-art in document detection and information extraction through multiple contract awards for different algorithmic approaches. Large scale text collections were tackled by the detection contractors, while domain and language portability were the challenge for the extraction contractors. The Text Retrieval Conference (TREC) and the Message Understanding Conferences (MUC) evaluated and baselined the technology developments. In contrast, TIPSTER Phase Two focused on creating an architecture to integrate the two technologies, and on deploying these technologies at multiple Government agencies. The deployments were called demonstration systems because their success in daily use would demonstrate the capabilities of the technologies to endusers. null As a demonstration system, the goal was to port Phase One technologies to Chinese. The University of Massachusetts ported their INQUERY system with the development of HanQuery. BBN ported many of the major components of PLUM to Chinese and created Named Entity Identification capabilities. This paper describes program and technical issues identified dunng the joint Government-contractor effort and shares lessons learned in these two areas.</Paragraph>
  </Section>
class="xml-element"></Paper>