<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-0705">
  <Title>Using Scenario Knowledge in Automatic Question Answering</Title>
  <Section position="4" start_page="32" end_page="32" type="intro">
    <SectionTitle>
2 Recognizing Contextual Entailment
</SectionTitle>
    <Paragraph position="0"> We de ne contextual entailment (CE) as a directional relation that exists between a text passage t and one of a set of implicit subquestions q that can be derived from a user's interpretation of a scenario. Informally, we consider that a scenario S contextually entails a passage t when there exists at least one subquestion q implied by S that can be considered to entail t.</Paragraph>
    <Paragraph position="1"> We expect that the meaning of an information-seeking scenario S can be represented as a question under discussion (QUD) QS, which denotes a partially-ordered set of subquestions (q [?] QS) that represent the entire set of questions that could potentially be asked in order to gather information relevant to S. Taken together, we expect these subquestions to represent the widest possible construal of a user's information need given S.</Paragraph>
    <Paragraph position="2">  We believe the set of subquestions implied by QS can be used to test whether a text passage is relevant to S. Since the formal answerhood relation between a question and its answer(s) can be cast in terms of (logical) entailment (Groenendijk, 1999; Lewis, 1988), we believe that systems for recognizing textual entailment (Dagan et al., 2005) could be used in order to identify those text passages that should be considered when gathering information related to a scenario. Based on these assumptions, we expect that the set of text passages that are textually entailed by subquestions derived from a scenario represent information that is more likely to be relevant to the overall topic of the scenario as a whole.</Paragraph>
    <Paragraph position="3"> We expect that there are three types of contextual entailment relationships that could prove useful for automatic Q/A systems. First, as illustrated in Case 1 in 1, CE could exist between a scenario and one of the set of answers returned by a Q/A system in response to a user's question. Second, as in Case 2, CE could be established directly between a scenario and the question asked by the user. Finally, as in Case 3, CE could be established both between a scenario and a user's question as well as between a scenario and one of the answers returned by the Q/A system for that question.</Paragraph>
    <Paragraph position="4"> Figure 2 provides examples of each of these three types of contextual entailment using the scenario presented in Figure 1.</Paragraph>
  </Section>
class="xml-element"></Paper>