<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-0506">
  <Title>Cooperative Question Answering in Restricted Domains: the WEBCOOP Experiment</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The current trend in Question Answering is towards the processing of large volumes of open-domain texts (e.g. documents extracted from the World Wide Web). Open domain QA is a hard task because no restriction is imposed either on the question type or on the user's vocabulary. This is why, most of the efforts (Voorhees, 2003) are focused on answering factoid style questions (and to a little extend, definition questions) using shallow text processing which is roughly based on pattern extraction or information retrieval techniques. However, QA should support the integration of deeper modes of language understanding as well as more elaborated reasoning schemas for more complex QA strategies, in order to provide, for example, better answer ranking, answer justification, responses to unanticipated questions or to resolve situations in which no answer is found in the data sources. Cooperative answering systems are typically designed to deal with such situations, by providing non-misleading, and useful answers to a query. (Grice, 1975) maxims of conversation namely the quality, quantity, relation and style maxims are frequently used as a basis for designing cooperative answering systems. An overview of cooperative answering techniques is given in (Gaasterland et al., 1994).</Paragraph>
    <Paragraph position="1"> In COGEX (Moldovan et al., 2003), a recent QA system, authors used automated reasoning for QA and showed that it is feasible, effective and scalable. This logical prover aims at checking and extracting all kinds of lexical relationships between the question and its candidate answers using world knowledge axioms, supplied by WordNet glosses, as well as rewriting rules representing equivalent classes of linguistic patterns. Such inference techniques (e.g. lexical equivalence, unification on logical representations of texts) are not sufficient for providing intelligent or cooperative responses. Indeed, advanced strategies for QA requires, as we explain in this paper, the integration of reasoning components operating over a variety of knowledge bases, encoding common sense knowledge as well as knowledge specific to a variety of domains. null We relate in this paper, an experiment for designing a logic based QA system, WEBCOOP, that integrates knowledge representation and advanced reasoning procedures to generate co-operative responses to natural language (NL) queries on the web. This experiment is first carried out on a relatively restricted domain that includes a number of aspects of tourism (accommodation and transportation, which have very different characteristics on the web). The tourism domain is in fact half way between an open domain and a closed domain (e.g. weather forecast, Unix technical manuals). The tourism domain has a kernel roughly around accommodation and transportation, but it also includes satellite domains, such as history, security, health, immigration, ecology, etc. Those satellite domains are only partly considered, from the point of view of the 'kernel' domains.</Paragraph>
    <Paragraph position="2"> We also observe that there is, in fact, a kind of continuum between the notions of open domain and closed domain, via restricted domains which makes quite fuzzy the definition of what a restricted domain is.</Paragraph>
    <Paragraph position="3"> Besides the technical functionalities of WEB-COOP, the main goal of this paper is to evaluate the different facets of the portability of WEBCOOP. Three major points are at stake: (1) resources, in term of language resources and kinds of knowledge required, (2) cooperative procedures involved, such as identifying and explaining user false presuppositions, relaxing constraints or providing intensional responses, and finally (3) the intelligibility of the system outputs (such as hyperlinks, short responses or list of answers), considering that answers should also include a trace of the inferences drawn.</Paragraph>
    <Paragraph position="4"> In the next sections, we briefly present the WEBCOOP architecture focusing on the kinds of knowledge and cooperative procedures involved. Then, we analyze the main characteristics of the tourism domain and outline its main features as a restricted domain. Then, we analyze the portability of this type of QA system to other restricted domains. Finally, we propose an evaluation methodology based on experimental psychology for the point (3) cited in the last paragraph.</Paragraph>
  </Section>
class="xml-element"></Paper>