Question Understanding in Community-Based Question Answering Systems

摘要

In this paper, we propose a novel method for community-based question answering task. The proposed method takes advantage of the bidirectional long short-term memory to represent questions and answers in combination with an attention mechanism. The attention model based on a multilayer perceptron captures important information in questions and their candidate sentences. We conduct experiments on public datasets, published by SemEval workshop. The experimental results show that our method achieves state-of-the-art performance.