Querying Web Data - The WebQA Approach

Source: CiteSeer

ABSTRACT The common paradigm of searching and retrieving information on the Web is based on keyword-based search using one or more search engines, and then browsing through the large number of returned URLs. This is significantly weaker than the declarative querying that is supported by DBMSs. The lack of a schema and the high volatility of Web make "database-like" querying of Web data difficult. In this paper we report on our work in building a system, called WebQA, that provides a declarative query-based approach to Web data retrieval that uses question-answering technology in extracting information from Web sites that are retrieved by search engines. The approach consists of first using meta-search techniques in an open environment to gather candidate responses from search engines and other on-line databases, and then using information extraction techniques to find the answer to the specific question from these candidates. A prototype system has been developed to test this approach. Testing includes evaluation of its performance as a question-answering system using a wellknown evaluation system called TREC-9. Its accuracy using TREC-9 data for simple questions is high and its retrieval performance is good. The system employs an open system architecture allowing for on-going improvements in various aspects.

  • Source
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a generic natural language processing (NLP) architecture, acronym QTIL, based on a system of cooperating multiple agents (Q/A, T, I, and L agents) which can be used in any information system incorporating Internet information retrieval. We then introduce a hybrid multi-agent system (MAS) architecture, acronym QTIP, for the privacy domain through integrating the PeCAN (personal context agent networking) and QTIL MAS architectures. There are two areas where NLP is used: in the user-MAS interaction and in the process of resource indexing and matching. These two areas map to the Q/A-agent and to the I-agents. We propose using a lightweight head-driven phrase structure grammar (HPSG) natural language method for the Q architectural layers and qualitatively justify its applicability. We provide an example of employing the HPSG formalism for information retrieval using natural language capability via privacy Web services in one instantiation of the QTIP architecture. Independent preliminary results for HPSG on the Q level show that our approaches for enhancing the usability of PET tools are promising.
    Web Intelligence, 2005. Proceedings. The 2005 IEEE/WIC/ACM International Conference on; 10/2005
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The MultiText QA System performs question answering using a two step passage selection method. In the first step, an arbitrary passage retrieval algorithm efficiently identifies hotspots in a large target corpus where the answer might be located. In the second step, an answer selection algorithm analyzes these hotspots, considering such factors as answer type and candidate redundancy, to extract short answer snippets. This chapter describes both steps in detail, with the goal of providing sufficient information to allow independent implementation. The method is evaluated using the test collection developed for the TREC 2001 question answering track.
    12/2005: pages 259-283;