<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-1026">
  <Title>Experiments with Interactive Question-Answering</Title>
  <Section position="3" start_page="205" end_page="206" type="intro">
    <SectionTitle>
2 Interactive Question-Answering
</SectionTitle>
    <Paragraph position="0"> We have found that the quality of interactions produced by an interactive Q/A system can be greatly enhanced by predicting the range of questions that a user might ask in the context of a given topic.</Paragraph>
    <Paragraph position="1"> If a large database of topic-relevant questions were available for a wide variety of topics, the accuracy of a state-of-the-art Q/A system such as (Harabagiu et al., 2003) could be enhanced.</Paragraph>
    <Paragraph position="2"> In FERRET, our interactive Q/A system, we store such &amp;quot;predicted&amp;quot; pairs of questions and answers in a database known as the Question Answer Database (or QUAB). FERRET uses this large set of topic-relevant question-and-answer pairs to improve the interaction with the user by suggesting new questions. For example, when a user asks a question like (Q1) (as illustrated in Table 1), FERRET returns an answer to the question (A1) and proposes (Q2), (Q3), and (Q4) as suggestions of possible continuations of the dialogue. Users then choose how to continue the interaction by either (1) ignoring the suggestions made by the system and proposing a different question, or by (2) selecting one of the proposed questions and examining its answer.</Paragraph>
    <Paragraph position="3"> Figure 1 illustrates the architecture of FERRET.</Paragraph>
    <Paragraph position="4"> The interactions are managed by a dialogue shell, which processes questions by transforming them into their corresponding predicate-argument structures2. null The data collection used in our experiments was 2We have employed the same representation of predicate-argument structures as those encoded in PropBank. We use a semantic parser (described in (Surdeanu et al., 2003)) that rec- null ognizes predicate-argument structures.</Paragraph>
    <Paragraph position="5"> (Q1) What weapons are included in Egypt's stockpiles? (A1) The Israelis point to comments made by former President Anwar Sadat, who in 1970 stated that Egypt has biological weapons stored in refrigerators ready to use against Israel if need be. The program might include &amp;quot;plague, botulism toxin, encephalitis virus, anthrax, Rift Valley fever and mycotoxicosis.&amp;quot; (Q2) Where did Egypt inherit its first stockpiles of chemical weapons? (Q3) Is there evidence that Egypt has dismantled its stockpiles of weapons? (Q4) Where are Egypt's weapons stockpiles located? (Q5) Who oversees Egypt's weapons stockpiles?  made available by the Center for Non-Proliferation Studies (CNS)3.</Paragraph>
    <Paragraph position="6"> Modules from the FERRET's dialogue shell interact with modules from the predictive dialogue block. Central to the predictive dialogue is the topic representation for each scenario, which enables the population of a Predictive Dialogue Network (PDN).</Paragraph>
    <Paragraph position="7"> The PDN consists of a large set of questions that were asked or predicted for each topic. It is a network because questions are related by &amp;quot;similarity&amp;quot; links, which are computed by the Question Similarity module. The topic representation enables an Information Extraction module based on (Surdeanu and Harabagiu, 2002) to find topic-relevant information in the document collection and to use it as answers for the QUABs. The questions associated with each predicted answer are generated from patterns that are related to the extraction patterns used for identifying topic relevant information. The quality of the dialog between the user and FERRET depends on the quality of the topic representations and the coverage of the QUABs.</Paragraph>
  </Section>
class="xml-element"></Paper>