通信学报2018，Vol.39Issue(2)：53-64,12.DOI:10.11959/j.issn.1000-436x.2018024
结合全局向量特征的神经网络依存句法分析模型
Neural network model for dependency parsing incorporating global vector feature
王衡军 1司念文 1宋玉龙 2单义栋1
作者信息
- 1. 解放军信息工程大学三院,河南 郑州 450001
- 2. 73671部队,安徽 六安 237000
- 折叠
摘要
Abstract
LSTM and piecewise CNN were utilized to extract word vector features and global vector features, respec-tively. Then the two features were input to feed forward network for training. In model training, the probabilistic training method was adopted. Compared with the original dependency paring model, the proposed model focused more on global features, and used all potential dependency trees to update model parameters. Experiments on Chinese Penn Treebank 5 (CTB5) dataset show that, compared with the parsing model using LSTM or CNN only, the proposed model not only re-mains the relatively low model complexity, but also achieves higher accuracies.关键词
依存句法分析/图模型/长短时记忆网络/卷积神经网络/特征Key words
dependency parsing/graph-based model/long short-term memory network/convolutional neural network/feature分类
信息技术与安全科学引用本文复制引用
王衡军,司念文,宋玉龙,单义栋..结合全局向量特征的神经网络依存句法分析模型[J].通信学报,2018,39(2):53-64,12.
