Identifying Irrelevant Answers in Web Based Question Answering Systems

Answer re-ranking and quality tagging are two major techniques used to address irrelevant answers in web-based community question answering systems (CQA). However, answer re-ranking is memory inefficient, and quality tagging lacks the ability to predict partially relevant responses. The reported precisions of both mechanisms are also low. Those facts emphasize the importance of finding alternative techniques for identifying irrelevant answers. In this paper, we have analyzed the capability of three widely popular deep learning models (CNN, LSTM and CLSTM) in the NLP literature to identify irrelevant answers in factoid and non-factoid systems. Further, we studied the ability of the same deep learning models to detect partially relevant answers in non-factoid systems. According to the results, the CLSTM model performed over CNN and LSTM in detecting irrelevant answers.