The paper is divided into three parts. The first part develops a framework explaining the need to disambiguate user inquiries to improve information systems and services. Theoretical grounds for this framework are explained for how questions are categorized based on their ambiguity type, while the relevant literature is briefly reviewed. The second part categorizes a set of questions, originally collected for TREC 8 QA Track, according to ambiguity type. Three types and two dimensions of ambiguity are identified by the author. The last part discusses three aspects of retrieval systems and services, based on the results of categorization: 1) increasing user input to make initial queries less ambiguous; 2) reducing search space by disambiguating queries; and 3) clustering search results based on the characteristics of prospective answers.
展开▼
