Automated FAQ Answering: Continued Experience with Shallow Language Understanding

Abstract

The subject of this research is development of an evolving automated FAQ (Frequently Asked Question) answering system that provides pre-stored answers to user questions asked in ordinary English. The natural language processing technique developed for FAQ retrieval does not analyze user queries; instead, analysis is applied to FAQs in the database long before any user queries are submitted. Thus, the work of FAQ retrieval is reduced to keyword matching without inferring; the system still creates an illusion of intelligence. Additional research is done in order to process phrases. The system is designed for ordinary websites such as those belonging to university laboratories, software developers, etc. Introduction People sitting in front of their computers expect quick solutions. People browsing a website want to get quick answers to their questions. In order to enable the latter, an evolving WWW-based automated FAQ answering system, which provides pre-stored answers to us...