基于分层注意力循环神经网络的司法案件刑期预测

doi:10.12068/j.issn.1005-3026.2022.03.006

东北大学学报（自然科学版） ›› 2022, Vol. 43 ›› Issue (3): 344-349.DOI: 10.12068/j.issn.1005-3026.2022.03.006

基于分层注意力循环神经网络的司法案件刑期预测

李大鹏^1,2，赵琪珲¹，邢铁军²，赵大哲¹

(1. 东北大学计算机科学与工程学院，辽宁沈阳110169; 2. 东软集团股份有限公司，辽宁沈阳110179)

修回日期:2021-01-26 接受日期:2021-01-26 发布日期:2022-05-18
通讯作者: 李大鹏
作者简介:李大鹏(1982-)，男，辽宁沈阳人，东北大学博士研究生；赵大哲(1960-)，女，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); 中央高校基本科研业务费专项资金资助项目(N171802001); 沈阳市科技计划项目(21-104-1-12).

Prison Term Prediction of Judicial Cases Based on Hierarchical Attentive Recurrent Neural Network

LI Da-peng^1,2， ZHAO Qi-hui¹， XING Tie-jun²， ZHAO Da-zhe¹

1. School of Computer Science & Engineering， Northeastern University， Shenyang 110169， China; 2. Neusoft Corporation， Shenyang 110179， China.

Revised:2021-01-26 Accepted:2021-01-26 Published:2022-05-18
Contact: LI Da-peng
About author:-
Supported by:
-

摘要/Abstract

摘要： 为了解决刑期预测任务准确率较差的问题，提出一种基于多通道分层注意力循环神经网络的司法案件刑期预测模型.该模型对传统的循环神经网络模型进行了改进，引入了BERT词嵌入、多通道模式和分层注意力机制，将刑期预测转化为文本分类问题.模型采用分层的双向循环神经网络对案件文本进行建模，并通过分层注意力机制在词语级和句子级两个层面捕获不同词语和句子的重要性，最终生成有效表征案件文本的多通道嵌入向量.实验结果表明:对比现有的基于深度学习的刑期预测模型，本文提出的模型具有更高的预测性能.

关键词: 刑期预测;分层注意力机制;双向门控循环单元;多通道;文本分类

Abstract: In order to solve the problem of poor accuracy of prison term prediction， a prison term prediction model was proposed on the basis of multi-channel hierarchical attentive recurrent neural network. The model improves the traditional recurrent neural network， introduces BERT word embedding， multichannel mode and hierarchical attention mechanism， and transforms the prison term prediction task into text classification problem. The model uses hierarchical bidirectional recurrent neural network to model the legal case text， and captures the importance of different words and sentences at word level and sentence level through hierarchical attention mechanism. Finally， a multi-channel embedding vector that effectively represents the case text is generated. The experimental results show that the proposed model has higher prediction performance compared with the existing prison term prediction model based on deep learning.

Key words: prison term prediction; hierarchical attention mechanism; bidirectional gated recurrent unit; multi-channel; text classification

中图分类号:

TP183

李大鹏，赵琪珲，邢铁军，赵大哲. 基于分层注意力循环神经网络的司法案件刑期预测[J]. 东北大学学报（自然科学版）, 2022, 43(3): 344-349.

LI Da-peng， ZHAO Qi-hui， XING Tie-jun， ZHAO Da-zhe. Prison Term Prediction of Judicial Cases Based on Hierarchical Attentive Recurrent Neural Network[J]. Journal of Northeastern University(Natural Science), 2022, 43(3): 344-349.

参考文献

[1]黄俏娟，罗旭东.人工智能与法律结合的现状及发展趋势［J］.计算机科学，2018，45(12):1-11.(Huang Qiao-juan，Luo Xu-dong.State-of-the-art and development trend of artificial intelligence combined with law［J］.Computer Science，2018，45(12):1-11.)
[2]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 Conference on Empirical Methods in Natural Language Processing.Copenhagen:ACL，2017:2727-2736.
[3]Vaswani A，Shazeer N，Parmar N，et al.Attention is all you need［C］ //Proceedings of the 31st International Conference on Neural Information Processing Systems.New York:MIT Press，2017:6000-6010.
[4]Devlin J，Chang M W，Lee K，et al.BERT:pre-training of deep bidirectional transformers for language understanding［C］ //Proceedings of the 57th Annual Conference of the Association for Computational Linguistics.Haikou:ACL，2019:4171-4186.
[5]陈剑，何涛，闻英友，等.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):1382-1388.(Chen Jian，He Tao，Wen Ying-you，et al.Entity recognition method for judicial documents based on BERT model ［J］.Journal of Northeastern University(Natural Science)，2020，41(10):1382-1388.)
[6]Li S，Zhang H L，Ye L，et al.MANN:a multichannel attentive neural network for legal judgment prediction［J］.IEEE Access，2019，7(1):151144-151154.
[7]Xu Z P，Li X，Li Y L，et al.Multi-task legal judgement prediction combining a subtask of the seriousness of charges［C］// Proceedings of the 19th China National Conference on Computational Linguistics.Haikou:Springer，2020:1132-1142.
[8]Xu N，Wang P H，Chen L，et al.Distinguish confusing law articles for legal judgment prediction ［C］//Proceedings of the 58th Annual Conference of the Association for Computational Linguistics.Seattle:ACL，2020:1022-1031.
[9]Bahdanau D，Cho K，Bengio Y.Neural machine translation by jointly learning to align and translate［C］// Proceedings of the International Conference on Learning Representations.San Diego:ICLR，2015:1-15.
[10]Xiao C J，Zhong H X，Guo Z P，et al.Overview of CAIL2018:legal judgment prediction competition ［EB/OL］.(2018-10-13)［2020-05-12］.https://arxiv.org/pdf/1810.05851.pdf.
[11]Kim Y.Convolutional neural networks for sentence classification［C］//Proceedings of the Conference on Empirical Methods in Natural Language Processing.Doha:ACL，2014:1746-1751.
[12]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:AAAI，2015:2267-2273.
[13]Rie J，Zhang T.Deep pyramid convolutional neural networks for text categorization ［C］//Proceedings of the 55th Annual Conference of the Association for Computational Linguistics.Vancouver:ACL，2017:562-570.
[14]Yang Z，Yang D，Dyer C，et al.Hierarchical attention networks for document classification ［C］ // Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.San Diego:ACL，2016:1480-1489.

基于分层注意力循环神经网络的司法案件刑期预测

Prison Term Prediction of Judicial Cases Based on Hierarchical Attentive Recurrent Neural Network

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 10

编辑推荐

Metrics

本文评价

[1]	翟莹莹，左丽，张恩德. 基于参数优化的RBF神经网络结构设计算法[J]. 东北大学学报:自然科学版, 2020, 41(2): 176-182.
[2]	张华伟，郑晓涛. 基于遗传算法优化神经网络的拼焊板压边力预测[J]. 东北大学学报:自然科学版, 2020, 41(2): 241-245.
[3]	于长永，何鑫，祁欣，马海涛. GMSDenseNet:基于组多结构卷积的轻量级DenseNet[J]. 东北大学学报:自然科学版, 2020, 41(1): 12-16.
[4]	蒋芳芳，徐敬傲，李任，徐礼胜. 基于CNN的心冲击信号阵发性房颤自动检测方法[J]. 东北大学学报:自然科学版, 2019, 40(11): 1539-1543.
[5]	王占山，康云云，牛海莎. 一类求解优化问题的神经网络及其全局吸引性分析[J]. 东北大学学报:自然科学版, 2017, 38(2): 153-157.
[6]	杨明，罗艳红，王义贺. 模型未知非零和博弈问题的策略迭代算法[J]. 东北大学学报:自然科学版, 2015, 36(3): 318-322.
[7]	韩鹏，郭天，汪晋宽，史泽伟. 基于mRMR-ESN的单变量光伏功率预测[J]. 东北大学学报（自然科学版）, 2021, 42(2): 174-179.
[8]	马海涛，路家蕊，于文鑫，于长永. 线性区域数量与PLNN表达能力的相关性[J]. 东北大学学报（自然科学版）, 2021, 42(2): 201-207.
[9]	蒋芳芳，王浩乾，程天庆，洪楚航. 基于相空间重构的心冲击信号房颤检测方法[J]. 东北大学学报（自然科学版）, 2021, 42(11): 1547-1554.
[10]	金瑾，王鹏. 历史数据驱动的多尺度量子谐振子优化算法[J]. 东北大学学报（自然科学版）, 2022, 43(2): 160-167.