![基于深度神经网络构建法律文本语法树的方法和装置](/CN/2016/1/109/images/201610546350.jpg)
基本信息:
- 专利标题: 基于深度神经网络构建法律文本语法树的方法和装置
- 申请号:CN201610546350.7 申请日:2016-07-12
- 公开(公告)号:CN106202010B 公开(公告)日:2019-11-26
- 发明人: 彭德光 , 李鹏华 , 孙健 , 利节 , 刘太林 , 赵芬
- 申请人: 重庆兆光科技股份有限公司
- 申请人地址: 重庆市沙坪坝区天星桥凤天大道109号2-2-1号
- 专利权人: 重庆兆光科技股份有限公司
- 当前专利权人: 重庆兆光科技股份有限公司
- 当前专利权人地址: 重庆市沙坪坝区天星桥凤天大道109号2-2-1号
- 代理机构: 重庆棱镜智慧知识产权代理事务所
- 代理人: 李兴寰
- 主分类号: G06F17/22
- IPC分类号: G06F17/22 ; G06N3/02
The invention provides a method and device for constructing a legal text syntax tree based on a deep neutral network. The method comprises the following steps: acquiring a training text of the legal service; performing word vector sparse representation on the training text; performing semantic annotation on the training text through the DNN according to the word vector sparse representation; performing dependency description on the training text according to the semantic annotation to construct the legal text syntax tree. The invention provides a systematic method to construct the syntax tree about technical language understanding in the legal service field, and the global-local training is used for solving the semantic bias problem in the legal language understanding.
公开/授权文献:
- CN106202010A 基于深度神经网络构建法律文本语法树的方法和装置 公开/授权日:2016-12-07