<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3006">
  <Title>Answering questions of Information Access Dialogue (IAD) task using ellipsis handling of follow-up questions</Title>
  <Section position="2" start_page="0" end_page="41" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In question answering task QAC of NTCIR (Kato et al., 2005)(Kato et al., 2004), interactive use of question answering is proposed as one of evaluation task called Information Access Dialogue (IAD) task, which was called subtask3 in QAC1,2. In IAD task, a set of question consists of one rst question and several follow-up questions. These series of questions and answers comprise an information access dialogue. In QAC1, there was only one follow-up question in a series of questions, but in QAC2 and 3 there were several follow-up questions.</Paragraph>
    <Paragraph position="1"> All follow-up questions have anaphoric expressions including zero anaphora which is frequently occurs in Japanese. There were several approaches to answer follow-up questions. One approach was to extract answers of follow-up questions from documents which were retrieved using clue words of the rst question (Sasaki et al., 2002). In the other approach, they added clue words extracted from the previous questions to clue words of follow-up question for document retrieval (Murata et al., 2002).</Paragraph>
    <Paragraph position="2"> However, when topic was changed in a series of questions, these approaches did not work well because clue words of the previous questions were not always effective to extract answer of the current question.</Paragraph>
    <Paragraph position="3"> Our approach is to handle ellipses of follow-up questions and apply the processed questions to ordinary question answering system which extracts answers of a question (Fukumoto et al., 2002)(Fukumoto et al., 2004)(Matsuda and Fukumoto, 2005). For QAC3, we have improved our previous approach to handle follow-up questions, that is, we have expanded ellipsis handling rules more precisely. Based on the analysis of evaluation results of QAC2, we have classi ed ellipsis pattern of question sentences into three types. The rst type is ellipsis using pronoun. This is the case that a word used in previous questions is replaced with pronoun. The second type is ellipsis of word in verb's obligatory case elements in the follow-up question. Some obligatory case elements of a verb of a follow-up question will be omitted and such elements also used in the previous question. The last type is ellipsis of a modi er or modi cand in a follow-up question. Such an ele- null ment appears in the previous question and has modi cation relationship with some word in the follow-up question sentence. In order to handle the above three ellipsis types, we utilized case information of main verb of a question and co-occurrence of nouns to recognize which case information is omitted. We used co-occurrence dictionary which was developed by Japan Electric Dictionary Research Inc. (EDR) (EDR, ).</Paragraph>
    <Paragraph position="4"> As for core QA system which is our main question answering system, we have integrated previous systems modules which are developed for QAC2.</Paragraph>
    <Paragraph position="5"> One module is to handle numeric type questions. It analyzes co-occurrence data of unit expression and their object names and detects an appropriate numeric type. Another module uses detailed classi cation of Named Entity for non numerical type questions such as person name, organization name and so on to extract an answer element of a given question.</Paragraph>
    <Paragraph position="6"> In the following sections, we will show the details of analysis of elliptical question sentences and our new method of ellipsis handling. We will also discuss our system evaluation on ellipsis handling.</Paragraph>
  </Section>
class="xml-element"></Paper>