面向裁判文书的司法知识抽取方法  

Judicial knowledge extraction method for judgement documents

作　　者：刘明伟 艾中良 刘忠麟[1] 王立才 黄杨琛 LIU Ming-wei;AI Zhong-liang;LIU Zhong-lin;WANG Li-cai;HUANG Yang-chen(North China Institute of Computing Technology,Beijing 100083,China;China Judicial Big Data Research Institute,Beijing 100043,China)

机构地区：[1]华北计算技术研究所,北京100083 [2]中国司法大数据研究院,北京100043

出　　处：《信息技术》2021年第6期51-57,共7页Information Technology

基　　金：国家重点研发计划项目(2018YFC0831206)。

摘　　要：运用人工智能技术对裁判文书进行司法知识抽取,是智慧司法领域的重要研究方向。文中针对传统的实体-关系抽取模型中对复杂关系和重叠关系识别不够准确的问题,面向裁判文书数据提出了一种基于级联二进制标记框架的司法知识抽取方法。对裁判文书中实体抽取和关系抽取两个任务进行了模型设计,并基于盗窃罪案由的裁判文书开展了算法实验,经实验验证,相比传统BERT模型,文中方法的F1值提升了0.119。Using artificial intelligence technology to extract judicial knowledge from judicial documents is an important research direction in the field of intelligent justice.In order to solve the problem that the traditional entity and relation extraction model is not accurate enough to identify complex and overlapping relations,this paper proposes a judicial knowledge extraction method based on cascaded binary markup framework for judicial document data.This paper designs the model of entity extraction and relation extraction in judicial documents,and carries out algorithm experiments based on the judgment documents of theft crime.The experiment results show that the F1 value of this method increases by 0.113 compared with the traditional Bert model.

关 键 词：裁判文书 知识抽取 实体识别 关系抽取 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]