Answering Questions for an Organization Online

Abstract

The World Wide Web continues to challenge organi-zations to make online access to their expertise con-venient for their clients. One means of expertise ac-cess that many clients find convenient in everyday life is asking natural language questions of the organiza-tion. To support it online, we developed an approach to building organization-embedded question-answering intermediaries, called Information Exchange systems. These systems use their knowledge of the organization’s structure to answer the clients ’ questions and to acquire new expertise from the organization’s experts. Our ap-proach uses techniques of hierarchical and predictive indexing, combined term weighting, abstraction-based retrieval, and negative evidence acquisition. We illus-trate our approach with the Chicago Information Ex-change system, an Information Exchange application embedded in one university’s computer science depart-ment.