<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-2047">
  <Title>Engineering Management The Chinese University of Hong Kong</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> Automatic reading comprehension (RC) systems can analyze a given passage and generate/extract answers in response to questions about the passage. The RC passages are often constrained in their lengths and the target answer sentence usually occurs very few times. In order to generate/extract a speci c precise answer, this paper proposes the integration of two types of deep linguistic features, namely word dependencies and grammatical relations, in a maximum entropy (ME) framework to handle the RC task. The proposed approach achieves 44.7% and 73.2% HumSent accuracy on the Remedia and ChungHwa corpora respectively.</Paragraph>
    <Paragraph position="1"> This result is competitive with other results reported thus far.</Paragraph>
  </Section>
class="xml-element"></Paper>