Syntax Tree Aware Adversarial Question Rewriting for Answer Selection

Answer selection is an important method to achieve better user experience in question answering (QA) systems and it is essential in ensuring better QA matching performance. Improving mutual information between QA pairs is a useful way to obtain the matching degree improvement and question rewriting has been proven a helpful way in utilizing mutual interaction between questions and answers. In this research, we focus on syntax tree aware question rewriting inspired by the thought of integrating syntactic information into question answering. Besides, to improve the quality of rewriting, we employ the generative adversarial network for rewriting optimization, which consists of a syntax tree aware rewriting model and a discriminator. The quality information given by the discriminator guides the optimizing of the rewriting model in the training phase. The experimental study has shown the effectiveness of syntax tree aware question rewriting and utilizing the generative adversarial network for rewriting.