A Novel Bidirectional LSTM and Attention Mechanism Based Neural Network for Answer Selection in Community Question Answering

作     者：Bo Zhang Haowen Wang Longquan Jiang Shuhan Yuan Meizi Li 

作者机构：College of InformationMechanical and Electrical EngineeringShanghai Normal UniversityShanghai200234China The Computer Science and Computer Engineering DepartmentUniversity of ArkansasFayettevilleAR72703USA 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2020年第62卷第3期

页      面：1273-1288页

核心收录：

学科分类：0502[文学-外国语言文学] 050201[文学-英语语言文学] 05[文学] 

基　　金：This work was supported in part by the National Natural Science Foundation of China under Grant 61572326,and Grant 61802258 the Natural Science Foundation of Shanghai under Grant 18ZR1428300 the Shanghai Committee of Science and Technology under Grant 17070502800 and Grant 16JC1403000 

主　　题：Question answering answer selection deep learning Bi-LSTM attention mechanisms 

摘      要：Deep learning models have been shown to have great advantages in answer selection *** existing models,which employ encoder-decoder recurrent neural network(RNN),have been demonstrated to be ***,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 *** this study,a new answer selection model is proposed based on the Bidirectional Long Short-Term Memory(Bi-LSTM)and attention *** proposed model is able to generate the more effective question-answer pair *** on a question answering dataset that includes information from multiple fields show the great advantages of our proposed ***,we achieve a maximum improvement of 3.8%over the classical LSTM model in terms of mean average precision.