Design and implementation of FAQ automatic return system based on similarity computation

Abstract

FAQ (frequently asked question) is widely used on the Internet, but most FAQ's asking and answering are not automatic. This paper introduces the design and implementation of a FAQ automatic return system based on semantic similarity computation, including computation model choosing, FAQ characters analyzing, FAQ data formal expressing, feature vector indexing, and weight computing and so on. According to FAQ features of sentence length short, two mapping, strong domain characteristics etc. Vector Space Model with special semantic process was selected in system, and corresponding algorithm of similarity computation was proposed too. Experiment shows that the system has a good performance for high frequent and common questions.