Open Access
ARTICLE
A Novel Bidirectional LSTM and Attention Mechanism Based Neural Network for Answer Selection in Community Question Answering
Bo Zhang1, Haowen Wang1, #, Longquan Jiang1, Shuhan Yuan2, Meizi Li1, *
1 College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai, 200234, China.
2 The Computer Science and Computer Engineering Department, University of Arkansas, Fayetteville, AR, 72703, USA.
# The author contributes equally to this work and should be considered co-first author.
* Corresponding Author: Meizi Li. Email: .
Computers, Materials & Continua 2020, 62(3), 1273-1288. https://doi.org/10.32604/cmc.2020.07269
Abstract
Deep learning models have been shown to have great advantages in answer
selection tasks. The existing models, which employ encoder-decoder recurrent neural
network (RNN), have been demonstrated to be effective. However, the traditional
RNN-based models still suffer from limitations such as 1) high-dimensional data
representation in natural language processing and 2) biased attentive weights for
subsequent words in traditional time series models. In this study, a new answer selection
model is proposed based on the Bidirectional Long Short-Term Memory (Bi-LSTM) and
attention mechanism. The proposed model is able to generate the more effective
question-answer pair representation. Experiments on a question answering dataset that
includes information from multiple fields show the great advantages of our proposed
model. Specifically, we achieve a maximum improvement of 3.8% over the classical
LSTM model in terms of mean average precision.
Keywords
Cite This Article
APA Style
Zhang, B., Wang, H., Jiang, L., Yuan, S., Li, M. (2020). A novel bidirectional LSTM and attention mechanism based neural network for answer selection in community question answering. Computers, Materials & Continua, 62(3), 1273-1288. https://doi.org/10.32604/cmc.2020.07269
Vancouver Style
Zhang B, Wang H, Jiang L, Yuan S, Li M. A novel bidirectional LSTM and attention mechanism based neural network for answer selection in community question answering. Comput Mater Contin. 2020;62(3):1273-1288 https://doi.org/10.32604/cmc.2020.07269
IEEE Style
B. Zhang, H. Wang, L. Jiang, S. Yuan, and M. Li "A Novel Bidirectional LSTM and Attention Mechanism Based Neural Network for Answer Selection in Community Question Answering," Comput. Mater. Contin., vol. 62, no. 3, pp. 1273-1288. 2020. https://doi.org/10.32604/cmc.2020.07269
Citations