《计算机应用研究》|Application Research of Computers

基于GRU和注意力机制的远程监督关系抽取

Distant supervision relationship extraction based on GRU and attention mechanism

免费全文下载 (已被下载 次)  
获取PDF全文
作者 黄兆玮,常亮,宾辰忠,孙彦鹏,孙磊
机构 桂林电子科技大学 广西可信软件重点实验室,广西 桂林 541004
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)10-010-2930-04
DOI 10.19734/j.issn.1001-3695.2018.03.0197
摘要 随着深度学习的发展,越来越多的深度学习模型被运用到了关系提取的任务中,但是传统的深度学习模型无法解决长距离依赖问题;同时,远程监督将会不可避免地产生错误标签。针对以上两个问题,提出一种基于GRU(gated recurrent unit)和注意力机制的远程监督关系抽取方法。首先通过使用GRU神经网络来提取文本特征,解决长距离依赖问题;接着在实体对上构建句子级的注意力机制,减小噪声句子的权重;最后在真实的数据集上,通过计算准确率、召回率并绘出PR曲线证明该方法与现有的一些方法相比,取得了比较显著的进步。
关键词 深度学习; 远程监督; 门控循环单元; 注意力机制
基金项目 国家自然科学基金资助项目(U1501252,61572146)
广西创新驱动重大专项项目(AA17202024)
广西自然科学基金资助项目(2016GXNSFDA380006)
广西信息科学实验中心平台建设项目(PT1601)
本文URL http://www.arocmag.com/article/01-2019-10-010.html
英文标题 Distant supervision relationship extraction based on GRU and attention mechanism
作者英文名 Huang Zhaowei, Chang Liang, Bin Chenzhong, Sun Yanpeng, Sun Lei
机构英文名 Guangxi Key Laboratory of Trusted Software,Guilin University of Electronic Technology,Guilin Guangxi 541004,China
英文摘要 With the development of deep learning, more and more deep learning models have been applied to the task of relation extraction, but traditional deep learning models can't solve long distance dependence problems. At the same time, distant supervision will inevitably generate wrong labels. For these two problems, this paper proposed a distant supervision relationship extraction method based on GRU(gated recurrent unit) and the attention mechanism. First, it adopted the GRU neural network to extract text features and solve long-distance dependence problems. Second, it constructed a sentence-level attention mechanism on entity pairs to reduce the weight of noise sentences. Finally, based on the real data set, by calculating the accuracy rate and recall rate, and drawing the PR curve to prove the proposed method has achieved significant progress compared with some existing methods.
英文关键词 deep learning; distant supervision; GRU; attention mechanism
参考文献 查看稿件参考文献
 
收稿日期 2018/3/19
修回日期 2018/4/28
页码 2930-2933
中图分类号 TP391
文献标志码 A