Automatic question answering system is a hot issue in the field of natural language processing, and is playing an increasingly important role in the long-distance teaching through networks. This paper proposes an ontology-based automatic question answering system model, at first, build restricted area ontology, then take advantage of the accurate description of concept as well as the definition of the relationship of the concepts, to expand keywords and improve the accuracy and recall rates.
Published in:
Computer Science and Software Engineering, 2008 International Conference on
(Volume:5
)
Date of Conference: 12-14 Dec. 2008