基于模板张量分解和双向LSTM的司法案件罪名认定

doi:10.12263/DZXB.20200098

电子学报 ›› 2021, Vol. 49 ›› Issue (4): 760-767.DOI: 10.12263/DZXB.20200098

基于模板张量分解和双向LSTM的司法案件罪名认定

李大鹏^1,2,3, 陈剑^2,3, 王晨^2,3, 闻英友^2,3, 赵大哲¹

1. 东北大学计算机科学与工程学院, 辽宁沈阳 110819;
2. 东北大学东软研究院, 辽宁沈阳 110819;
3. 辽宁省工业控制安全技术工程中心, 辽宁沈阳 110819

收稿日期:2020-01-15 修回日期:2020-09-22 出版日期:2021-04-25
- 通讯作者:
- 李大鹏
- 作者简介:
- 陈剑男,1980年9月出生,东北大学副教授,硕士生导师,主要研究方向为人工智能、网络与信息安全.E-mail:chen.jian@neusoft.com
- 基金资助:
- 国家自然科学基金 (No.61972079，No.61772126）; 国家重点研发计划 (No.2018YFC0830601）; 教育部基本科研业务费 (No.171802001，No.2016002，No.2016004）; 辽宁省重点研发计划 (No.2019JH2/10100027）; 辽宁省"兴辽英才"计划项目 (No.XLYC1802100）

Conviction in Judicial Cases Based on Template Tensor Decomposition and Bidirectional LSTM

LI Da-peng^1,2,3, CHEN Jian^2,3, WANG Chen^2,3, WEN Ying-you^2,3, ZHAO Da-zhe¹

1. School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning 110819, China;
2. Neusoft Group Research, Northeastern University, Shenyang, Liaoning 110819, China;
3. Research Center of Safety Engineering Technology in Industrial Control of Liaoning Province, Shenyang, Liaoning 110819, China

Received:2020-01-15 Revised:2020-09-22 Online:2021-04-25 Published:2021-04-25

摘要/Abstract

摘要： 案件罪名认定是司法业务的重要环节，尚缺乏有效的智能辅助工具和手段.针对案件定罪的难点问题，提出一种结合张量分解和双向LSTM （Long Short-Term Memory）神经网络的案件定罪方法.该方法将案件数据表示为张量，并在张量分解过程中引入模板张量.模板张量可以在双向LSTM神经网络分类模型的训练过程不断的被优化，使得分解后的核心张量包含更加有效的张量结构和特征信息，有助于提高后续分类模型的准确性，实现案件罪名的精准认定.实验结果表明：所提出的基于张量分解和双向LSTM的司法案件定罪方法比现有方法具有更好的准确性.

关键词: 张量分解, 双向长短期记忆, 模板张量, 案件定罪, 文本分类

Abstract: Conviction in judicial cases is an important part of judicial business,but there is still a lack of effective intelligent auxiliary tools and methods.Aiming at the difficult problem of conviction in judicial cases,a method combining tensor decomposition and Bi-LSTM neural network is proposed.This method represents the case data as a tensor and introduces a template tensor in the tensor decomposition process.The template tensor can be continuously optimized during the training process of Bi-LSTM neural network classification model,so that the decomposed core tensor contains more effective tensor structure and feature information,which is helpful to improve the accuracy of the subsequent classification model and realize the accurate conviction in judicial cases.The experimental results show that the proposed method for conviction in judicial cases based on tensor decomposition and Bi-LSTM has better accuracy than the existing methods.

Key words: tensor decomposition, Bi-LSTM, template tensor, conviction in judicial cases, text classification

中图分类号:

TP183

李大鹏, 陈剑, 王晨, 闻英友, 赵大哲. 基于模板张量分解和双向LSTM的司法案件罪名认定[J]. 电子学报, 2021, 49(4): 760-767.

LI Da-peng, CHEN Jian, WANG Chen, WEN Ying-you, ZHAO Da-zhe. Conviction in Judicial Cases Based on Template Tensor Decomposition and Bidirectional LSTM[J]. Acta Electronica Sinica, 2021, 49(4): 760-767.

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.(in Chinese)
[2] Octavia-Maria S,Marcos Z,Shervin M,Mihaela V,Liviu P D,Josef V G.Exploring the use of text classification in the legal domain[A].Proceedings of the Second Workshop on Automated Semantic Analysis of Information in Legal Texts[C].London,UK:ACM,2017.22-27.
[3] Octavia-Maria S,Marcos Z,Mihaela V,Josef V G.Predicting the law area and decisions of French supreme court cases[A].Proceedings of the International Conference Recent Advances in Natural Language Processing[C].Varna,Bulgaria:ACM,2017.56-63.
[4] 林志宏,池宏,许保光.基于卷积神经网络的公安案件文本语义特征提取方法研究[J].数学的实践与认识,2017,46(17):129-142. Lin Zhi-hong,Chi Hong,Xu Bao-guang.Research of criminal case semantic feature extraction method based on the convolutional neural network[J].Mathematics in Practice and Theory,2017,46(17):129-142.(in Chinese)
[5] Xiao G Y,Mo J Q,Even C,Chen H.Multi-task CNN for classification of Chinese legal questions[A].IEEE 14th International Conference on e-Business Engineering[C].Shanghai,China:IEEE,2017.126-132.
[6] Guo X D,Zhang H L,Ye L,Li S.Learning users' intention of legal consultation through pattern-oriented tensor decomposition with Bi-LSTM[J].Wireless Communications and Mobile Computing,2019,32(3):1-16.
[7] Kolda T G,Bader B W.Tensor decompositions and applications[J].SIAM Review,2009,51(3):455-500.
[8] Chen T,Xu R F,He Y L,Wang X.Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN[J].Expert Systems with Applications,2017,72(4):221-230.
[9] Tucker LR.Some mathematical notes on three-mode factor analysis[J].Psychometrika,1966,31(3):279-311.
[10] Harshman RA.Foundations of the PARAFAC procedure:Models and conditions for an "explanatory" multimodal factor analysis[J].UCLA Working Papers in Phonetics,1970,45(16):1-84.
[11] Vozalis M G,Margaritis K G.Using SVD and demographic data for the enhancement of generalized collaborative filtering[J].Information Sciences,2007,177(15):3017-3037.
[12] Kim Y.Convolutional neural networks for sentence classification[A].Proceedings of the 2014 Conference on empirical methods in natural language processing[C].Doha,Qatar:ACL,2014.1746-1751.
[13] Donahue J,Hendricks L A,Guadarrama S.Long-term recurrent convolutional networks for visual recognition and description[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Boston,USA:IEEE,2015.2625-2634.
[14] Cho K,Bart V M,Caglar G,Fethi M.Learning phrase representations using RNN encoder-decoder for statistical machine translation[A].Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing[C].Doha,Qatar:ACL,2014.1724-1734.
[15] Donahue J,Hendricks L A,Guadarrama S.Ask the GRU:Multitask learning for deep text recommendations[A].Proceedings of the 10th ACM Conference on Recommender Systems[C].Como,Italy:ACM,2016.107-114.

基于模板张量分解和双向LSTM的司法案件罪名认定

Conviction in Judicial Cases Based on Template Tensor Decomposition and Bidirectional LSTM

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

[1]	张昱, 刘开峰, 张全新, 王艳歌, 高凯龙. 基于组合-卷积神经网络的中文新闻文本分类[J]. 电子学报, 2021, 49(6): 1059-1067.
[2]	唐焕玲, 郑涵, 刘艳红, 马思源, 窦全胜, 鲁明羽. Tr-SLDA:一种面向交叉领域的迁移主题模型[J]. 电子学报, 2021, 49(3): 605-613.
[3]	陈金立, 王亚鹏, 李家强, 龙伟军. 冲击噪声下基于张量分解和K‑means聚类的MIMO雷达阵列诊断[J]. 电子学报, 2021, 49(12): 2315-2322.
[4]	吴玉佳, 李晶, 宋成芳, 常军. 基于高效用神经网络的文本分类方法[J]. 电子学报, 2020, 48(2): 279-284.
[5]	脱婷, 马慧芳, 李志欣, 赵卫中. 熵权约束稀疏表示的短文本分类算法[J]. 电子学报, 2020, 48(11): 2131-2137.
[6]	唐焕玲, 窦全胜, 于立萍, 宋英杰, 鲁明羽. 有监督主题模型的SLDA-TC文本分类新方法[J]. 电子学报, 2019, 47(6): 1300-1308.
[7]	肖云鹏, 刘晏驰, 刘红, 刘媛妮. 一种基于动态角色标识和张量分解的推荐模型[J]. 电子学报, 2018, 46(3): 569-574.
[8]	胡小娟, 刘磊, 邱宁佳. 基于主动学习和否定选择的垃圾邮件分类算法[J]. 电子学报, 2018, 46(1): 203-209.
[9]	葛素楠, 韩敏. 基于四阶累积张量方法的欠定盲源信号分离[J]. 电子学报, 2014, 42(5): 992-997.
[10]	闫瑞;曹先彬;李凯. 面向短文本的动态组合分类算法[J]. 电子学报, 2009, 37(5): 1019-1024.
[11]	唐焕玲, 林正奎, 鲁明羽. 基于差异性评估对Co-training文本分类算法的改进[J]. 电子学报, 2008, 36(S1): 138-143.
[12]	戴新宇;田宝明;周俊生;陈家骏. 一种基于潜在语义分析和直推式谱图算法的文本分类方法LSASGT[J]. 电子学报, 2008, 36(8): 1626-1630.
[13]	刘桃, 刘秉权, 徐志明, 王晓龙. 领域术语自动抽取及其在文本分类中的应用[J]. 电子学报, 2007, 35(2): 328-332.