<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3005">
  <Title>A Data Driven Approach to Relevancy Recognition for Contextual Question Answering</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Question Answering (QA) is an interactive human-machine process that aims to respond to users' natural language questions with exact answers rather than a list of documents. In the last few years, QA has attracted broader research attention from both the information retrieval (Voorhees, 2004) and the computational linguistic fields (http://www.clt.mq.edu.au/Events/ Conferences/acl04qa/). Publicly accessible web-based QA systems, such as AskJeeves (http://www.ask.com/) and START (http://start.csail.mit.edu/), have scaled up [?]The work was done when the first author was visiting</Paragraph>
  </Section>
class="xml-element"></Paper>