Table of Content

Open Access iconOpen Access



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: email.

Computers, Materials & Continua 2020, 62(3), 1273-1288.


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.


Cite This Article

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," Computers, Materials & Continua, vol. 62, no.3, pp. 1273–1288, 2020.


cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 6604


  • 3376


  • 0


Share Link