<?xml version="1.0" standalone="yes"?>
<Paper uid="N03-2026">
  <Title>Desparately Seeking Cebuano</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The Los Angeles Times reported that at about 5:20 P.M.</Paragraph>
    <Paragraph position="1"> on Tuesday March 4, 2003, a bomb concealed in a backpack exploded at the airport in Davao City, the second largest city in the Philippines. At least 23 people were reported dead, with more than 140 injured, and President Arroyo of the Philippines characterized the blast as a terrorist act. With the 13 hour time difference, it was then 4:20 A.M on the same date in Washington, DC.</Paragraph>
    <Paragraph position="2"> Twenty-four hours later, at 4:13 A.M. on March 5, participants in the Translingual Information Detection, Extraction and Summarization (TIDES) program were notified that Cebuano had been chosen as the language of interest for a &amp;quot;surprise language&amp;quot; practice exercise that had been planned quite independently to begin on that date. The notification observed that Cebuano is spoken by 24% of the population of the Philippines, and that it is the lingua franca in the south Philippines, where the event occurred.</Paragraph>
    <Paragraph position="3"> One goal of the TIDES program is to develop the ability to rapidly deploy a broad array of language technologies for previously unforeseen languages in response to unexpected events. That capability will be formally exercised for the first time during June 2003, in a monthlong &amp;quot;Surprise Language Experiment.&amp;quot; To prepare for that event, the Linguistic Data Consortium (LDC) organized a &amp;quot;dry run&amp;quot; for March 5-14 in order to refine procedures for rapidly developing language resources of the type that the TIDES community will need during the July evaluation.</Paragraph>
    <Paragraph position="4"> Development of interactive Cross-Language Information Retrieval (CLIR) systems that can be rapidly adapted to accommodate new languages has been the focus of extensive collaboration between the University of Maryland and The Johns Hopkins University, and more recently with the University of Southern California. The capability for rapid development of necessary language resources is an essential part of that process, so we had been planning to participate in the surprise language dry run to refine our procedures for sharing those resources with other members of the TIDES community. Naturally, we chose CLIR as a driving application to focus our effort. Our goal, therefore, was to build an interactive system that would allow a searcher posing English queries to find relevant Cebuano news articles from the period immediately following the bombing.</Paragraph>
  </Section>
class="xml-element"></Paper>