结合网络表示学习和文本卷积网络的类案发现

doi:10.3778/j.issn.1002-8331.2007-0407

摘要/Abstract

摘要： 作为“智慧法院”的核心应用之一，相似裁判文书的发现有助于解决司法过程中裁判尺度不统一、类案不同、量刑不规范等问题。目前，一部分方法侧重于从裁判文书中总结领域特征，并将这些特征融入到语言模型中来提升相似文书发现的效果。另一部分工作将其转化为分类任务，利用有监督学习模型来进行建模与预测。然而，已有的方法没有考虑将语言模型与分类模型各自的优势进行结合。为此，提出一种基于网络表示学习（network representation learning）和文本卷积网络（convolutional neural network for texts）的类案发现方法。方法分别从无监督学习与有监督学习的视角来建模裁判文书中的信息，并根据法律知识体系对原有模型的负采样方法（negative sampling）进行改进。最终，方法设计了一种较为合理的投票机制将两类模型的结果进行融合。实验结果表明，提出的联合方法较已有方法能在类案发现任务中取得更高的推送准确率。

关键词: 类案发现, 网络表示学习, 卷积神经网络, 投票机制

Abstract: As one of the core applications of smart court, the discovery of similar judgment documents can help to solve the problems of inconsistent judgment standards, different case types, and irregular sentencing in the judicial process. At present, some of the existing methods focus on summarizing field features from judicial documents into text processing methods for improving the performances of similar judgment documents discovery. Other works transform the case discovery into classification problems and employ supervised learning models to obtain the results. However, current methods do not consider combining the advantages of above models together. To fill this gap, a method based on network representation learning and convolutional neural network for texts is proposed for similar case discovery. It encodes the information of judicial documents in view of unsupervised learning and supervised learning, and improves the negative sampling strategies of original models based on legal knowledge system. Finally, the method merges the outputs of two models by the designed voting mechanism. Experimental results indicate that the proposed method can obtain better performances than existing methods in terms of accuracy rate.

梁鸿翔, 张步烨, 李炜卓, 程茜雅. 结合网络表示学习和文本卷积网络的类案发现[J]. 计算机工程与应用, 2022, 58(2): 153-160.

LIANG Hongxiang, ZHANG Buye, LI Weizhuo, CHENG Xiya. Combining Network Representation Learning and Text Convolutional Neural Network for Similar Case Discovery[J]. Computer Engineering and Applications, 2022, 58(2): 153-160.

参考文献

[1] 陈琨.类案发现嵌入“智慧法院”办案场景的原理和路径[J].中国应用法学，2018（4）：88-97.
CHEN Kun.Principles and paths of case pushes embedded in “smart court” case scenarios[J].China Review of Administration of Justice，2018（4）：88-97.
[2] 朱彬彬，祝兴栋.类案发现的精细化：问题、成因与改进——以刑事类案发现为例[J].法律适用（司法案例），2018（20）：90-98.
ZHU Binbin，ZHU Xingdong.The refinement of the discovery of similar cases：problems，causes and improvements[J].Journal of Law Application（Judicial Case），2018（20）：90-98.
[3] 王君泽，马洪晶，张毅，等.裁判文书类案发现中的案情相似度计算模型研究[J].计算机工程与科学，2019，41（12）：2193-2201.
WANG Junze，MA Hongjing，ZHANG Yi，et al.A case similarity calculation model in case pushing of judicial documents[J].Computer Engineering & Science，2019，41（12）：2193-2201.
[4] 王禄生.司法大数据与人工智能开发的技术障碍[J].中国法律评论，2018（2）：46-53.
WANG Lusheng.Technical obstacles in the development of judicial big data and artificial intelligence[J].China Law Review，2018（2）：46-53.
[5] MINOCHA A，SINGH N，SRIVASTAVA A.Finding relevant indian judgments using dispersion of citation network[C]//Proceedings of the 24th International Conference on World Wide Web，Italy，2015：1085-1088.
[6] KUMAR S.Similarity analysis of legal judgments and applying ‘Paragraph-link’ to find similar legal judgments[D].Hyderabad：International Institute of Information Technology，2014.
[7] 邓丁朋，周亚建，池俊辉，等.短文本分类技术研究综述[J].软件，2020，41（2）：141-144.
DENG Dingpeng，ZHOU Yajian，CHI Junhui，et al.A summary of the research on short text classification[J].Computer Engineering & Software，2020，41（2）：141-144.
[8] 张宇艺，左亚尧，陈小帮.基于改进的CBOW与ABiGRU的文本分类研究[J].计算机工程与应用，2019，55（24）：135-140.
ZHANG Yuyi，ZUO Yayao，CHEN Xiaobang.Text classification research based on improved CBOW and ABiGRU[J].Computer Engineering and Applications，2019，55（24）：135-140.
[9] 刘心惠，陈文实，周爱，等.基于联合模型的多标签文本分类研究[J].计算机工程与应用，2020，56（14）：111-117.
LIU Xinhui，CHEN Wenshi，ZHOU Ai，et al.Multi-label text classification based on joint model[J].Computer Engineering and Application，2020，56（14）：111-117.
[10] 陈文哲，秦永彬，黄瑞章，等.基于犯罪行为序列的法律条文预测方法[J].计算机工程与应用，2019，55（22）：245-249.
CHEN Wenzhe，QIN Yongbin，HUANG Ruizhang，et al.Improved approach to TF-IDF algorithm in text classification[J].Computer Engineering and Application，2019，55（22）：245-249.
[11] 蒋勇青，于洋.文献相似性检测技术及其应用[J].情报工程，2018，4（3）：96-104.
JIANG Yongqing，YU Yang.Research on literature similarity detection technology and its applications[J].Technology Intelligence Engineering，2018，4（3）：96-104.
[12] 施聪莺，徐朝军，杨晓江.TFIDF算法研究综述[J].计算机应用，2009，29（S1）：167-170.
SHI Congying，XU Chaojun，YANG Xiaojiang.Study of TFIDF algorithm[J].Journal of Computer Applications，2009，29（S1）：167-170.
[13] HOFMANN T.Probabilistic latent semantic analysis[C]//Proceedings of the 5th Conference on Uncertainty in Artificial Intelligence，Australia，1999：289-296.
[14] BLEI D M，NG A Y，JORDAN M I.Latent Dirichlet allocation[J].Journal of Machine Learning Research，2003（3）：993-1022.
[15] LE Q，MIKOLOV T.Distributed representations of sentences and documents[C]//Proceedings of the 31th International Conference on Machine Learning，China，2014：1188-1196.
[16] MIKOLOV T，SUTSKEVER I，CHEN K，et al.Distributed representations of words and phrases and their compositionality[C]//Proceedings of the Annual Conference on Neural Information Processing Systems，USA，2013：3111-3119.
[17] DEVLIN J，CHANG M W，LEE K，et al.{BERT：} pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics：Human Language Technologies，USA，2019：4171-4186.
[18] VASWANI A，SHAZEER N，PARMAR N，et al.Attention is all you need[C]//Proceedings of the Annual Conference on Neural Information Processing Systems，USA，2017：5998-6008.
[19] 涂存超，杨成，刘知远，等.网络表示学习综述[J].中国科学：信息科学，2017，47（8）：980-996.
TU Cunchao，YANG Cheng，LIU Zhiyuan，et al.Network representation learning：an overview[J].Scientia Sinica（Informationis），2017，47（8）：980-996.
[20] TANG J，QU M，WANG M，et al.LINE：large-scale information network embedding[C]//Proceedings of the 24th International Conference on World Wide Web，Italy，2015：1067-1077.
[21] KIM Y.Convolutional neural networks for sentence classification[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing，Qatar，2014：1746-1751.
[22] LIU P，QIU X，HUANG X.Recurrent neural network for text classification with multi-task learning[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence，USA，2016：2873-2879.
[23] JOULIN A，GRAVE E，BOJANOWSKI P，et al.Bag of tricks for efficient text classification[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics，Spain，2017：3-7.
[24] TANG J，QU M，MEI Q.PTE：predictive text embedding through large-scale heterogeneous text networks[C]//Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，Australia，2016：1165-1174.
[25] PEROZZI B，AL-RFOU R，SKIENA S.Deepwalk：online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，USA，2014：701-710.
[26] CAO S，LU W，XU Q.GraRep：learning graph representations with global structural information[C]//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management，Australia，2015：891-900.
[27] GROVER A，LESKOVEC J.node2vec：scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，USA，2016：855-864.