文章摘要
Xu Yilong (徐翼龙)*,Li Wenfa**,Wang Gongming*** ****,Huang Lingyun*****.[J].高技术通讯(英文),2020,26(4):442~447
A multi-target stance detection based on Bi-LSTM network with position-weight
  
DOI:10.3772/j.issn.1006-6748.2020.04.012
中文关键词: 
英文关键词: long short-term memory (LSTM), multi-target, natural language processing, stance detection
基金项目:
Author NameAffiliation
Xu Yilong (徐翼龙)* (*Smart City College, Beijing Union University, Beijing 100101, P.R.China) 
Li Wenfa** (**College of Robotics, Beijing Union University, Beijing 100101, P.R.China) 
Wang Gongming*** **** (***Tianyuan Network Co., Ltd., Beijing 100193, P.R.China) (****Beijing Tianyuan Network Co., Ltd., Beijing 100193, P.R.China) 
Huang Lingyun***** (*****Chinatelecom Information Development Co., Ltd., Beijing 100093, P.R.China) 
Hits: 1624
Download times: 1690
中文摘要:
      
英文摘要:
      In the task of multi-target stance detection, there are problems the mutual influence of content describing different targets, resulting in reduction in accuracy. To solve this problem, a multi-target stance detection algorithm based on a bidirectional long short-term memory (Bi-LSTM) network with position-weight is proposed. First, the corresponding position of the target in the input text is calculated with the ultimate position-weight vector. Next, the position information and output from the Bi-LSTM layer are fused by the position-weight fusion layer. Finally, the stances of different targets are predicted using the LSTM network and softmax classification. The multi-target stance detection corpus of the American election in 2016 is used to validate the proposed method. The results demonstrate that the Bi-LSTM network with position-weight achieves an advantage of 1.4% in macro average F1 value in the comparison of recent algorithms.
View Full Text   View/Add Comment  Download reader
Close

分享按钮