基于图注意力网络的案件罪名预测方法:CP-GAT

doi:10.12068/j.issn.1005-3026.2021.12.002

东北大学学报（自然科学版） ›› 2021, Vol. 42 ›› Issue (12): 1681-1687.DOI: 10.12068/j.issn.1005-3026.2021.12.002

基于图注意力网络的案件罪名预测方法:CP-GAT

赵琪珲¹，李大鹏²，高天寒¹，闻英友³

(1. 东北大学软件学院，辽宁沈阳110169; 2. 东北大学计算机科学与工程学院，辽宁沈阳110169; 3. 东北大学计算机科学与工程学院/东软研究院，辽宁沈阳110169)

修回日期:2021-03-25 接受日期:2021-03-25 发布日期:2021-12-17
通讯作者: 赵琪珲
作者简介:赵琪珲(1992-)，男，辽宁沈阳人，东北大学博士研究生；高天寒(1978-)，男，辽宁沈阳人，东北大学教授，博士生导师；闻英友(1974-)，男，辽宁沈阳人，东北大学教授，博士生导师.
基金资助:
国家重点研发计划项目(2018YFC0830601) .

A Charge Prediction Method Based on Graph Attention Network: CP-GAT

ZHAO Qi-hui¹， LI Da-peng²， GAO Tian-han¹， WEN Ying-you³

1. Software College， Northeastern University， Shenyang 110169， China; 2. School of Computer Science and Engineering， Northeastern University， Shenyang 110169， China; 3. School of Computer Science and Engineering /Neusoft Research Institute， Northeastern University， Shenyang 110169， China.

Revised:2021-03-25 Accepted:2021-03-25 Published:2021-12-17
Contact: GAO Tian-han
About author:-
Supported by:
-

摘要/Abstract

摘要： 案件罪名预测任务是基于文本数据去预测案件所属罪名.针对现有方法在相似罪名和长尾数据集上表现不佳的问题，提出了一种基于图注意力网络的案件罪名预测方法CP-GAT(charge prediction based on graph attention network).该方法首先使用司法文书数据集中的案例事件描述文本和案例对应的法条信息建立异质图结构数据，构建后的异质图包含两种类型的节点(词节点、案例节点)，两种类型的边(词节点与词节点相连的边，词节点与案例节点相连的边).在基于法律文本构建后的异质图上使用图注意力网络进行图特征提取，最后将得到的特征向量输入到罪名预测的分类器中，得到案例所属的罪名.在CAIL2018法律数据集上的实验结果表明，基于图注意力网络的罪名预测方法优于对比实验使用的方法，准确率和宏观F1值分别达到了95.2%和66.1，验证了提出的方法有利于提升案件罪名预测任务的性能.

关键词: 图注意力网络;罪名预测;节点特征提取;异质图;法条信息

Abstract: The task of charge prediction is to predict the charge of a case based on text data. Aiming at the problem that the existing methods do not perform well on similar charges and long tail datasets， a case charge prediction method was proposed based on graph attention network(CP-GAT). Firstly， the case event description text in the judicial document data set and the corresponding legal information of the case are used to establish the heterogeneous graph structure data. The constructed heterogeneous graph contains two types of nodes(word nodes and case nodes)， two types of edges(the edges connected by word nodes and word nodes， the edges connected by word nodes and case nodes). The graph attention network was used to extract graph features on the heterogeneous graph constructed based on texts， and finally the obtained feature vector was input into the classifier of charge prediction to get the charge of the case. The experimental results on the CAIL2018 legal dataset show that the charge prediction method based on graph attention network is better than the model used in the comparative experiment， and the accuracy and macro F1 value reach 95.2% and 66.1 respectively， which verifies that the proposed method is conducive to improving the performance of the case charge prediction task.

Key words: graph attention network; charge prediction; node feature extraction; heterogeneous graph; law article information

中图分类号:

TP391

赵琪珲，李大鹏，高天寒，闻英友. 基于图注意力网络的案件罪名预测方法:CP-GAT[J]. 东北大学学报（自然科学版）, 2021, 42(12): 1681-1687.

ZHAO Qi-hui， LI Da-peng， GAO Tian-han， WEN Ying-you. A Charge Prediction Method Based on Graph Attention Network: CP-GAT[J]. Journal of Northeastern University(Natural Science), 2021, 42(12): 1681-1687.

参考文献

[1]Zhong H X，Xiao C J，Tu C C，et al.How does NLP benefit legal system:a summary of legal artificial intelligence ［C］// Proceedings of the 58th Annal Meeting of the Association for Computational Linguistics.Online，2020:5218-5230.
[2]李强，李瑶坤，夏书月，等.一种改进的医疗文本分类模型:LS-GRU［J］.东北大学学报(自然科学版)，2020，41(7):938-943.(Li Qiang， Li Yao-kun， Xia Shu-yue，et al.An improved medical text classification model:LS-GRU［J］.Journal of Northeastern University(Natural Science)， 2020，41(7):938-943.)
[3]Kort F.Predicting supreme court decisions mathematically:a quantitative analysis of the right to counsel cases［J］.American Political Science Review，1957，51(1):1-12.
[4]Nagel S S.Applying correlation analysis to case prediction［J］.Texas Law Review，1964，42(7):1006-1017.
[5]Liu C L，Hsieh C D.Exploring phrase-based classification of judicial documents for criminal charges in Chinese ［C］// Proceedings of International Symposium on Methodologies for Intelligent Systems.Bari，2006:681-690.
[6]Liu Y H，Chen，Y L，Ho，W L.Predicting associated statutes for legal problems［J］.Information Processing & Management，2015，51(1):194-211.
[7]Katz D M，Nd B M，Blackman J.A general approach for predicting the behavior of the supreme court of the united states［J］.Plos One，2014，12(4):e0174698.
[8]Luo B F，Feng Y S，Xu J B，et al.Learning to predict charges for criminal cases with legal basis ［C］// Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.Copenhagen，2017:2727-2736.
[9]Jiang X，Ye H，Luo Z C，et al.Interpretable rationale augmented charge prediction system ［C］//Proceedings of the 27th International Conference on Computational Linguistics:System Demonstration.Santa Fe:ACL，2018:146-151.
[10]Long S B，Tu C C，Liu Z Y，et al.Automatic judgment prediction via legal reading comprehension［EB/OL］.［2021-01-10］.arXiv preprint arXiv:1809.0653.
[11]Zhong H X，Guo Z P，Tu C C，et al.Legal judgment prediction via topological learning ［C］// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.Brussels，2018:3540-3549.
[12]Duan W，Li L.An external knowledge enhanced multi-label charge prediction approach with label number learning［EB/OL］.［2021-01-10］.arXiv:1907.02205v1.
[13]Velikovi P，Cucurull G，Casanova A，et al.Graph attention networks ［C］//Proceedings of the 6th International Conference on Learning Representations.Vancouver，2018:1-12.
[14]Yao L，Mao C S，Luo Y.Graph convolutional networks for text classification ［J］.Proceedings of the AAAI Conference on Artificial Intelligence，2019，33:7370-7377..
[15]Xiao C J，Zhong H X，Guo Z P，et al.CAIL2018:a large-scale legal dataset for judgment prediction［EB/OL］.［2021-01-10］.arXiv preprint arXiv:1809.0653.
[16]Salton G，Buckley C.Term-weighting approaches in automatic text retrieval［J］.Information Processing & Management， 1988，24(5):513-523.
[17]Kipf T N，Welling M.Semi-supervised classification with graph convolutional networks ［C］// Proceedings of the 5 th International Conference on Learning Representations.Toulon，2017:1-14.
[18]Li Y，Tarlow D，Brockschmidt M，et al.Gated graph sequence neural networks ［C］// Proceedings of the 4th International Conference on Learning Representations.San Juan，2016:1-20.
[19]Suykens J A，Vandewalle J.Least squares support vector machine classifiers［J］.Neural Processing Letters，1999，9(3):293-300.
[20]Kim Y.Convolutional neural networks for sentence classification［C］// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing.Doha，2014:1746-1751.
[21]Lai S W，Xu L H，Liu K，et al.Recurrent convolutional neural networks for text classification［C］// Proceedings of the 29th National Conference on Artificial Intelligence.Austin，2015:2267-2273.
[22]Yang Z，Yang D，Dyer C，et al.Hierarchical attention networks for document classification ［C］// Proceedings of the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.San Diego，2016.
[23]Li Z，Sun M.Punctuation as implicit annotations for Chinese word segmentation［J］.Computational Linguistics，2009，35(4):505-512.
[24]Mikolov T，Chen K，Corrado G，et al.Efficient estimation of word representations in vector space ［C］// Proceedings of International Conference on Intelligent Text Processing and Computational Linguistics.Berlin:Springer，2013:430-443.
[25]Kingma D P，Ba J.Adam:a method for stochastic optimization ［C］// The 3rd International Conference for Learning Representations.San Diego，2015:1-15.

基于图注意力网络的案件罪名预测方法:CP-GAT

A Charge Prediction Method Based on Graph Attention Network: CP-GAT

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	庞彦伟，苏畅，龙涛. 自适应构造与聚合多尺度代价体的双目立体匹配[J]. 东北大学学报（自然科学版）, 2023, 44(4): 457-468.
[2]	丁其川，王力，刘成. 融合长距离信道注意力与病理特征的肺结节分类[J]. 东北大学学报（自然科学版）, 2023, 44(4): 476-485.
[3]	李海燕，熊立昌，郭磊，李海江. 基于U-net边缘生成和超图卷积的两阶段修复算法[J]. 东北大学学报（自然科学版）, 2023, 44(3): 331-339.
[4]	杨丹，刘国如，任梦成，裴宏杨. 多尺度卷积核U-Net模型的视网膜血管分割方法[J]. 东北大学学报（自然科学版）, 2021, 42(1): 7-14.
[5]	韩东红，张宏亮，朱帅伟，齐孝龙. 面向新浪微博的情感社区检测算法[J]. 东北大学学报（自然科学版）, 2021, 42(1): 21-31.
[6]	原培新，陈鼎夫. 双能X射线高动态范围安检图像压缩算法[J]. 东北大学学报（自然科学版）, 2021, 42(1): 96-101.
[7]	魏颖, 徐楚翘, 刁兆富, 李伯群. 基于生成对抗网络的多目标行人跟踪算法[J]. 东北大学学报（自然科学版）, 2020, 41(12): 1673-1680.
[8]	李稷，徐安军. 炼钢车间多天车动态调度仿真方案[J]. 东北大学学报:自然科学版, 2020, 41(12): 1699-1707.
[9]	李占山，吕艾娜. 基于新冗余度的特征选择方法[J]. 东北大学学报:自然科学版, 2020, 41(11): 1550-1556.
[10]	王鑫，王翠荣，王聪，苑迎. 双通道多感知卷积神经网络图像超分辨率重建[J]. 东北大学学报:自然科学版, 2020, 41(11): 1564-1570.
[11]	张春雷，戴丽，刘宇，李鹤. 基于三点法和ICP算法的手术导航系统患者配准[J]. 东北大学学报:自然科学版, 2020, 41(11): 1584-1590.
[12]	陈剑，何涛，闻英友，马林涛. 基于BERT模型的司法文书实体识别方法[J]. 东北大学学报:自然科学版, 2020, 41(10): 1382-1387.
[13]	张田，田勇，王子，王昭东. 基于清晰度评价的自适应阈值图像分割法[J]. 东北大学学报:自然科学版, 2020, 41(9): 1231-1238.
[14]	张丽杰，刘建昌，谭树彬. 复杂建筑火灾中的人员疏散路径多目标规划[J]. 东北大学学报:自然科学版, 2020, 41(6): 761-766.
[15]	赵海，周冰玲，朱宏博，窦圣昶. 基于连续最大流的三维肺实质快速分割算法[J]. 东北大学学报:自然科学版, 2020, 41(4): 470-474.