Adaptive natural language interfaces to FAQ knowledge bases

fn this paper, we present a natural language interface architecture, which is used for accessing FAQ knowledge bases. Since one of the main obstacles to the efficient use of natural language interfaces is the high amount of r equired manual knowledge engineering, we provide an adaptive architecture t o automate the acquisition of linguistic knowledge. We apply a machine lear ning module based on an eXtended Semantic Enumeration (XSE) tree to activat e linguistic tests from semantic, syntactic, and pragmatic analyses during the traversal of the tree. The XSE-tree is built automatically based on pas t questions without the need for any additional linguistic knowledge. (C) 2 000 Elsevier Science B.V. All rights reserved.