Skip to main content
Modeling Reference Interviews as a Basis for Improving Automatic QA Systems
HLT-NAACL 2006 Workshop on Interactive Question Answering
  • N. J. McCracken
  • Anne R. Diekema, Utah State University
  • G. Ingersoll
  • S. C. Harwell
  • E. E. Allen
  • O. Yilmazel
  • E. D. Liddy
Document Type
Conference Paper
Association for Computational Linguistics
Publication Date

The automatic QA system described in this paper uses a reference interview model to allow the user to guide and contribute to the QA process. A set of system capabilities was designed and implemented that defines how the user’s contributions can help improve the system. These include tools, called the Query Template Builder and the Knowledge Base Builder, that tailor the document processing and QA system to a particular domain by allowing a Subject Matter Expert to contribute to the query representation and to the domain knowledge. During the QA process, the system can interact with the user to improve query terminology by using Spell Checking, Answer Type verification, Expansions and Acronym Clarifications. The system also has capabilities that depend upon, and expand the user’s history of interaction with the system, including a User Profile, Reference Resolution, and Question Similarity modules.

Originally published by the Association for Computational Linguistics. Publisher's PDF available through remote link.
Citation Information
McCracken, N. J., Diekema, A. R., Ingersoll G., Harwell, S. C., Allen, E. E., Yilmazel, O., Liddy E. D. Modeling Reference Interviews as a Basis for Improving Automatic QA Systems. In: HLT-NAACL 2006 Workshop on Interactive Question Answering. New York, New York, June 8-9, 2006, p. 17-24.