<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-1625">
  <Title>Answer Generation with Temporal Data Integration</Title>
  <Section position="7" start_page="0" end_page="0" type="evalu">
    <SectionTitle>
5 Evaluation
</SectionTitle>
    <Paragraph position="0"> We evaluate our approach by applying our answer selection method to 72 questions expecting an answer of type date.</Paragraph>
    <Paragraph position="1"> Among these questions, 36 questions expected an answer of type date and 36 expected an temporal interval.</Paragraph>
    <Paragraph position="2"> These 72 questions were submitted to QRISTAL. Applying our answer selection process (called Cont.Det. in the following tables), we distinguish several cases: either the proposed answer is correct, or it is incorrect or the proposed answer is included in the interval defining the exact date of the event or the answer is incomplete. We note &amp;quot;impossible&amp;quot; cases when it is impossible to select an answer (when all candidate answers have the same occurrence frequency).</Paragraph>
    <Paragraph position="3">  We compare the results of our content determination method not only to QRISTAL's results but also to the results obtained by a &amp;quot;most frequent answer&amp;quot; method. Our approach obtains better results on questions expecting an answer of type temporal interval and particularly on questions about iterative events (for example, When does the next X take place? When did the first Y happen?, ...). This is partly due to the fact that a &amp;quot;most frequent answer&amp;quot; method, for example, is not able to solve temporal references.</Paragraph>
    <Paragraph position="4"> Among the &amp;quot;incorrect&amp;quot; answers, most errors can be explained by the fact that some incorrect candidate answers introduce a bias in the calculation of the average duration.</Paragraph>
    <Paragraph position="5"> A way to solve this problem is to eliminate some candidate answers by analysing in more depth their contexts of occurrence. Linguistic information and semantic knowledge about answer concepts may allow to determine if a candidate answer selected by QRISTAL is appropriate or not, incomplete, etc.</Paragraph>
  </Section>
class="xml-element"></Paper>