In this paper, the answer selection problem in community question answering (CQA) is regarded as an answer sequence labeling task, and a novel approach is proposed based on the recurrent architecture for this problem. Our approach applies convolution neural networks (CNNs) to learning the joint representation of questionanswer pair firstly, and then uses the joint representation as input of the long shortterm memory (LSTM) to learn the answer sequence of a question for labeling the matching quality of each answer. Experiments conducted on the SemEval 2015 CQA dataset shows the effectiveness of our approach.
CITATION STYLE
Zhou, X., Hu, B., Chen, Q., Tang, B., & Wang, X. (2015). Answer sequence learning with neural networks for answer selection in community question answering. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference (Vol. 2, pp. 713–718). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/p15-2117
Mendeley helps you to discover research relevant for your work.