中文法律条文推荐深度学习方法综述  

Survey on Chinese Law Articles Recommendation with Deep Learning

作　　者：彭亚男 尹华 贺敏伟 PENG Yanan;YIN Hua;HE Minwei(School of Information,Guangdong University of Finance and Economics;Guangdong Intelligent Business Engineering Technology Research Center,Guangzhou 510320,China)

机构地区：[1]广东财经大学信息学院 [2]广东省智能商务工程技术研究中心,广东广州510320

出　　处：《软件导刊》2023年第12期245-252,共8页Software Guide

基　　金：教育部人文社会科学研究青年基金项目(21YJCZH202)。

摘　　要：法律条文推荐是判决预测的关键任务,旨在根据法律文书的案情描述和事实预测案件所涉及的法律条文。传统的基于机器学习的方法难以提取案情描述的深层特征,近年来基于深度学习的方法取得了较好的推荐效果。从中文法条推荐模型的构建模式、深度学习方法以及复杂应用场景等多个视角系统梳理现有研究成果,重点以卷积神经网络、循环神经网络、图神经网络以及混合模型为索引,分析其在中文法律条文推荐中的应用,并在公开数据集上比较中文法律条文推荐深度学习算法的性能。通过分析现有研究,总结出数据集构造、复杂场景及可解释性问题是未来中文法律条文推荐研究面临的挑战。The recommendation of legal provisions is a key task in judgment prediction,aiming to predict the legal provisions involved in the case based on the description of the legal documents and the facts.Traditional machine learning based methods are difficult to extract deep fea⁃tures of case descriptions,and in recent years,deep learning based methods have achieved good recommendation results.Systematically re⁃view existing research results from multiple perspectives such as the construction mode,deep learning methods,and complex application sce⁃narios of Chinese legal article recommendation models,with a focus on using convolutional neural networks,recurrent neural networks,graph neural networks,and hybrid models as indexes to analyze their applications in Chinese legal article recommendation.Compare the perfor⁃mance of deep learning algorithms for Chinese legal article recommendation on public datasets.By analyzing existing research,it is concluded that the construction of datasets,complex scenarios,and interpretability issues will be the challenges faced by future research on the recom⁃mendation of Chinese legal provisions.

关 键 词：中文法律条文推荐 深度学习 判决预测 文本表示 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]