<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-2028">
  <Title>Spoken Interactive ODQA System: SPIQA</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Open-domain QA (ODQA), which extracts answers from large text corpora, such as newspaper texts, has been intensively investigated in the Text REtrieval Conference (TREC). ODQA systems return an actual answer in response to a question written in a natural language. However, the information in the first question input by a user is not usually sufficient to yield the desired answer. Interactions for collecting additional information to accomplish QA are needed. To construct more precise and user-friendly ODQA systems, a speech interface is used for the interaction between human beings and machines.</Paragraph>
    <Paragraph position="1"> Our goal is to construct a spoken interactive ODQA system that includes an automatic speech recognition (ASR) system and an ODQA system.</Paragraph>
    <Paragraph position="2"> To clarify the problems presented in building such a system, the QA systems constructed so far have been classified into a number of groups, depending on their target domains, interfaces, and interactions to draw out additional information from users to accomplish set tasks, as is shown in Table 1. In this table, text and speech denote text input and speech input, respectively. The term &amp;quot;addition&amp;quot; represents additional information queried by the QA systems.</Paragraph>
    <Paragraph position="3"> This additional information is separate to that derived from the user's initial questions.</Paragraph>
    <Paragraph position="4">  To construct spoken interactive ODQA systems, the following problems must be overcome: 1. System queries for additional information to extract answers and effective interaction strategies using such queries cannot be prepared before the user inputs the question. 2. Recognition errors degrade the performance of QA systems. Some information indispensable for extracting answers is deleted or substituted with other words.</Paragraph>
    <Paragraph position="5"> Our spoken interactive ODQA system, SPIQA, copes with the first problem by adopting disambiguating users' questions using system queries. In addition, a speech summarization technique is applied to handle recognition errors.</Paragraph>
  </Section>
class="xml-element"></Paper>