Open Access Open Access  Restricted Access Subscription or Fee Access

A Predictive Search Method for FAQ-based Question Answering System

Masaki Samejima, Yuichi Saito, Masanori Akiyoshi, Hironori Oka


We address a predictive search for FAQ-based question answering system in online help desk. The predictive search is to search FAQ corresponding to a user’s question that the user is inputting with important words defined in each FAQ. The important words co-occur in a user’s question and the rates of the co-occurrences depend on which FAQ the user’s question corresponds to. The co-occurrence rates of important words in questions are estimated from a statistical model of important words co-occurrence generated with past questions and FAQ corresponding to them. When the highest co-occurrence rate of them is larger than a threshold set on each FAQ, the question is regarded as a corresponding FAQ. Through an evaluation experiment by using practical data in the help desk, it has been confirmed that the proposed method can improve the recall rate for short questions and the precision rate for long questions.


help desk, predictive search, FAQ based question answering, statistical model of word co-occurrence.

Full Text:


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.