面向借贷案件的相似案例匹配模型

doi:10.19678/j.issn.1000-3428.0066055

摘要/Abstract

摘要：

相似案例匹配任务是文本匹配在司法领域的具体应用之一，目的在于区分法律文书是否相似，对类案检索具有重要意义。与传统文本匹配任务相比，法律文本通常篇幅较长，同时相似案例匹配是针对相同案由案件的匹配，案情文本之间的差异较小，以往的文本匹配方法很难计算文本相似度。针对借贷案件文本匹配存在的问题，建立一种融合借贷案件关键要素的相似案例匹配模型。为了获取文本中更丰富的语义特征，构建正则表达式获得借贷案件的特定案件要素，如借款交付形式、借款人基本属性等，并与原有的案情文本相结合，联合学习法律文本与案件关键要素的语义特征。同时，利用共享权重的预训练模型分别对不同的文书进行编码，并且对预训练模型特定编码层的输出进行融合，得到更加丰富的语义信息。引入有监督对比学习框架，更好地利用样本信息，进一步提高相似案例匹配的性能。在CAIL2019-SCM数据集上的实验结果表明，与LFESM模型相比，该模型在测试集上的准确率提高了1.05个百分点。

关键词: 相似案例匹配, 孪生网络, 对比学习, 预训练模型, 法律关键要素

Abstract:

The purpose of Similar Case Matching(SCM) is to distinguish whether legal documents are similar, which is a specific application of text matching and is vital to the retrieval of similar cases. Compared with conventional texts, legal texts are typically longer, and SCM aims to realize matching for the same case. Moreover, the difference between case texts is negligible; therefore, calculating text similarity using previous text-matching methods is challenging. This study establishes a SCM model that integrates key elements of lending cases to address the issues of text matching in lending cases. To obtain richer semantic features from texts, regular expressions are constructed to obtain specific case elements of lending cases, such as the loan-delivery form and the basic attributes of borrowers, which are then combined with the original case text to jointly learn the semantic features of the legal text and key elements of the case. Additionally, pretrained models with shared weights are used to encode different instruments separately, and the outputs of specific encoding layers of the pretrained models are fused to obtain richer semantic information. Finally, the proposed model incorporates a supervised comparison learning framework to utilize the text information more effectively and further improve the performance of SCM. Experiments on the CAIL2019-SCM dataset show that this model improves the accuracy of the test set by 1.05 percentage points compared with LFESM models.

曹发鑫, 孙媛媛, 王治政, 潘丁豪, 林鸿飞. 面向借贷案件的相似案例匹配模型[J]. 计算机工程, 2024, 50(1): 306-312.

Faxin CAO, Yuanyuan SUN, Zhizheng WANG, Dinghao PAN, Hongfei LIN. Similar Case Matching Model for Lending Cases[J]. Computer Engineering, 2024, 50(1): 306-312.

http://www.ecice06.com/CN/Y2024/V50/I1/306

图/表 6

参考文献 25

1	王景林, 吴宜霖. 类案检索制度在司法实践中的应用研究. 法制博览, 2022, (2): 100- 102.
	WANG J L, WU Y L. Research on the application of similar case retrieval system in judicial practice. Legality Vision, 2022, (2): 100- 102.
2	XIAO C J, ZHONG H X, GUO Z P, et al. CAIL2019-SCM: a dataset of similar case matching in legal domain[EB/OL]. [2022-09-16]. https://arxiv.org/abs/1911.08962.pdf.
3	CONNEAU A, KIELA D, SCHWENK H, et al. Supervised learning of universal sentence representations from natural language inference data[C]//Proceedings of 2017 Conference on Empirical Methods in Natural Language Processing. Philadelphia, USA: Association for Computational Linguistics, 2017: 670-680.
4	REIMERS N, GUREVYCH I. Sentence-BERT: sentence embeddings using Siamese BERT-networks[EB/OL]. [2022-09-16]. https://arxiv.org/abs/1908.10084.pdf.
5	DAS D, SMITH N A. Paraphrase identification as probabilistic quasi-synchronous recognition[C]//Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP. Philadelphia, USA: Association for Computational Linguistics, 2009: 468-476.
6	卜质琼, 郑波尽. 基于LDA模型的Ad hoc信息检索方法研究. 计算机应用研究, 2015, 32 (5): 1369- 1372. doi: 10.3969/j.issn.1001-3695.2015.05.022
	BU Z Q, ZHENG B J. Ad hoc information retrieval method based on LDA. Application Research of Computers, 2015, 32 (5): 1369- 1372. doi: 10.3969/j.issn.1001-3695.2015.05.022
7	吕正东, 李航. 深度匹配学习在语言匹配中的应用. 中国计算机学会通讯, 2015, 8 (8): 30- 38.
	LÜ Z D, LI H. Apply deep matching learning in language matching. Communication of China Computer Federation, 2015, 8 (8): 30- 38.
8	HUANG P S, HE X D, GAO J F, et al. Learning deep structured semantic models for web search using click through data[C]//Proceedings of the 22nd ACM International Conference on Information & Knowledge Management. New York, USA: ACM Press, 2013: 2333-2338.
9	SHEN Y L, HE X D, GAO J F, et al. A latent semantic model with convolutional-pooling structure for information retrieval[C]//Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management. New York, USA: ACM Press, 2014: 101-110.
10	PANG L A, LAN Y Y, GUO J F, et al. Text matching as image recognition[C]//Proceedings of AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2016: 2793-2799.
11	CHEN Q, ZHU X D, LING Z H, et al. Enhanced LSTM for natural language inference[EB/OL]. [2022-09-16]. https://arxiv.org/abs/1609.06038.pdf.
12	DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of 2019 Conference of the North American Chapter of Association for Computational Linguistics: Human Language Technologies, Volume 1(Long and Short Papers). Philadelphia, USA: Association for Computational Linguistics, 2019: 4171-4186.
13	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, USA: ACM Press, 2017: 6000-6010.
14	LI B H, ZHOU H, HE J X, et al. On the sentence embeddings from pre-trained language models[EB/OL]. [2022-09-16]. https://arxiv.org/abs/2011.05864.pdf.
15	SU J L, CAO J R, LIU W J, et al. Whitening sentence representations for better semantics and faster retrieval[EB/OL]. [2022-09-16]. https://arxiv.org/abs/2103.15316.pdf.
16	PEINELT N, NGUYEN D, LIAKATA M. tBERT: topic models and BERT joining forces for semantic similarity detection[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: Association for Computational Linguistics, 2020: 7047-7055.
17	GAO T Y, YAO X C, CHEN D Q. SimCSE: simple contrastive learning of sentence embeddings[EB/OL]. [2022-09-16]. https://arxiv.org/abs/2104.08821.pdf.
18	JAWAHAR G, SAGOT B, SEDDAH D. What does BERT learn about the structure of language?[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: Association for Computational Linguistics, 2019: 3651-3657.
19	LIU Y H, OTT M, GOYAL N, et al. RoBERTa: a robustly optimized BERT pretraining approach[EB/OL]. [2022-09-16]. https://arxiv.org/abs/1907.11692.pdf.
20	PALANGI H, DENG L, SHEN Y L, et al. Deep sentence embedding using long short-term memory networks: analysis and application to information retrieval. ACM Transactions on Audio, Speech, and Language Processing, 2016, 24 (4): 694- 707. doi: 10.1109/TASLP.2016.2520371
21	HU B T, LU Z D, LI H, et al. Convolutional neural network architectures for matching natural language sentences[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. New York, USA: ACM Press, 2014: 2042-2050.
22	SU J L, LU Y, PAN S F, et al. RoFormer: enhanced Transformer with rotary position embedding[EB/OL]. [2022-09-16]. https://arxiv.org/abs/2104.09864.pdf.
23	DING S Y, SHANG J Y, WANG S H, et al. ERNIE-doc: a retrospective long-document modeling Transformer[EB/OL]. [2022-09-16]. https://arxiv.org/abs/2012.15688.pdf.
24	HONG Z L, ZHOU Q F, ZHANG R, et al. Legal feature enhanced semantic matching network for similar case matching[C]//Proceedings of 2020 International Joint Conference on Neural Networks. Washington D. C., USA: IEEE Press, 2020: 1-8.
25	PENNINGTON J, SOCHER R, MANNING C. GloVe: global vectors for word representation[C]//Proceedings of 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: Association for Computational Linguistics, 2014: 1532-1543.

[1]	顾嘉静, 杨丹, 聂铁铮, 寇月. 基于多视图融合跨层对比学习的推荐算法[J]. 计算机工程, 2024, 50(1): 120-128.
[2]	张博旭, 蒲智, 程曦. 基于提示学习的维吾尔语文本分类研究[J]. 计算机工程, 2023, 49(6): 292-299,313.
[3]	朱红, 牛浩然, 朱彤. 基于字词融合与对抗训练的行业人物实体识别[J]. 计算机工程, 2023, 49(5): 56-62.
[4]	李晓腾, 张盼盼, 勾智楠, 高凯. 基于多任务学习的多模态命名实体识别方法[J]. 计算机工程, 2023, 49(4): 114-119.
[5]	廖列法, 谢树松. 基于注意力机制特征融合的中文命名实体识别[J]. 计算机工程, 2023, 49(4): 256-262.
[6]	王春雷, 张建林, 李美惠, 徐智勇, 魏宇星. 结合卷积Transformer的目标跟踪算法[J]. 计算机工程, 2023, 49(4): 281-288,296.
[7]	吴雪莹, 段友祥, 昌伦杰, 李世银, 孙歧峰. 面向地质领域的实体关系联合抽取研究[J]. 计算机工程, 2023, 49(3): 121-127.
[8]	吴奇林, 党亚固, 熊山威, 吉旭, 毕可鑫. 基于混合特征网络的学生评教文本情感分析模型[J]. 计算机工程, 2023, 49(11): 24-29, 39.
[9]	王曙燕, 郭睿涵, 孙家泽. 基于图对比学习的MOOC推荐方法[J]. 计算机工程, 2023, 49(1): 57-64,72.
[10]	茹妞妞, 于晋伟, 杨卫华, 卞玮. 基于压缩与精化深度体素流模型的视频插值[J]. 计算机工程, 2022, 48(9): 248-253.
[11]	吴迪, 王梓宇, 赵伟超. ELMo-CNN-BiGRU双通道文本情感分类模型[J]. 计算机工程, 2022, 48(8): 105-112.
[12]	邢彤彤, 孙仁诚, 邵峰晶, 隋毅. 深度学习中的权重初始化方法研究[J]. 计算机工程, 2022, 48(7): 104-113.
[13]	王刚, 孙媛媛, 陈彦光, 林鸿飞. 面向法律文书的分段式摘要模型[J]. 计算机工程, 2022, 48(6): 288-294.
[14]	刘高军, 李亚欣, 段建勇. 基于混合注意力机制的中文机器阅读理解[J]. 计算机工程, 2022, 48(10): 67-72,80.
[15]	杨帅东, 谌海云, 徐钒诚, 赵书朵, 袁杰敏. 基于孪生区域建议网络的无人机目标跟踪算法[J]. 计算机工程, 2022, 48(1): 288-295,304.

选择文件类型/文献管理软件名称

选择包含的内容