Question Answering from Frequently Asked Question Files: Experiences with the FAQ Finder System

This paper describes FAQ Finder, a natural language question-answering system that uses files of frequently-asked questions as its knowledge base. Unlike AI question-answering systems that focus on the generation of new answers, FAQ Finder retrieves existing ones found in frequently-asked question files. Unlike information retrieval approaches that rely on a purely lexical metric of similarity between query and document, FAQ Finder uses a semantic knowledge base (WordNet) to improve its ability to match question and answer. We describe the design considerations that have entered into the system and various experiments that influence the systems current implementation. We include results from an evaluation of the systems performance against a corpus of user questions, and show that a combination of semantic and statistical techniques works better than any single approach. Introduction In the vast information space of the Internet, individuals and groups have created small pockets of ...