Improving question retrieval in community question answering with label ranking

Community question answering services (CQA), which provides a platform for people with diverse backgrounds to share information and knowledge, has become an increasingly popular research topic recently as made popular by sites such as Yahoo! Answers¹, answerbag², zhidao³, etc. Question retrieval (QR) in CQA can automatically find the most relevant and recent questions that have been solved by other users. Current QR approaches typically consider using diverse retrieval models, but they fail to analyze users´ intention. User intentions such as finding facts, interacting with others, seeking reasons, etc. reflect what the users really want to know. Hence, we propose to integrate user intention analysis into QR. Firstly, we classify questions into different and multiple types of users´ intentions. Another practical problem is that there naturally exist some preferences among the possible questions types. The more relevant type should be ranked higher than types which are not so relevant. Therefore, we propose to utilize a novel label ranking method, which is a machine learning algorithm that aims to predict a ranking among all the possible labels, to perform question classification. Secondly, based on the result of question classification, we integrate user intentions with translation-based language models to explore whether a user´s intention does help to improve the performance. We conduct a series of experiments with Yahoo data, and the experimental results demonstrate that our proposed improved question retrieval can indeed enhance the performance of traditional question retrieval model.