Improving Question Recommendation by Exploiting Information Need

Shuguang Li and Suresh Manandhar
Computer Science Department, University of York


Abstract

In this paper we address the problem of question recommendation from large archives of community question answering data by exploiting the usage of users' information needs. Our experimental results indicate that questions based on the same or similar information need can provide good question recommendation candidates for the query question. We show that translation model can be effectively utilized to predict the information need given only the user's query question. Experiments show that the proposed information need prediction approach can improve the performance of question recommendation.




Full paper: http://www.aclweb.org/anthology/P/P11/P11-1143.pdf