基于多任务学习的多罪名案件信息联合抽取

doi:10.3778/j.issn.1002-8331.2108-0344

摘要/Abstract

摘要： 面向法律文本的实体关系联合抽取技术对于案情关键信息的智能提取至关重要，是智慧司法领域应用中的重要环节。目前的联合抽取方法虽然已经在特定罪名案件的数据集上取得了较好的效果，但是由于模型在训练时只关注了特定罪名类型文本数据的特点，使得模型的泛化能力有限，在应用到多罪名案件的情况下常常使得模型的效果下降。因此引入多任务学习的方法对多罪名情形下的实体关系联合抽取进行了研究，以涉毒类案件和盗窃类案件两大类罪名的文书数据为基础，构建了一个罪名分类任务作为联合抽取的辅助任务，通过基于特征筛选的动态加权多任务模型同时对两个任务进行学习，在单任务模型的基础上整体F1值提升了2.4个百分点，在涉毒类案件和盗窃类案件上的F1值分别提升了1.6和3.2个百分点。

关键词: 实体关系联合抽取, 多任务学习, 智慧司法

Abstract: Joint entity recognition and relation extraction on legal documents is important for automatic extraction of the crucial information of the legal cases. And it is a crucial part for legal intelligence application. The current triplet extraction methods have achieved good results on specific crime cases, while since these models only pay attention to the text features of specific crime type during training, the generalization ability of the model is limited, which usually leads to a decrease in the performance when applying to multi-crime legal documents. Therefore, it leverages the multi-task learning method for triplet extraction on multi-crime legal documents. The experiments are based on two categories of crimes involving drug-related cases and larceny-related cases. It constructs a crime classification task as auxiliary task and trains the two tasks simultaneously by the dynamic weight with feature filtering multi-task model. From the experimental results, compared with the single-task model, this model improves the F1 value by 2.4 percentage points on the whole, by 1.6 and 3.2 percentage points on drug-related cases and larceny-related cases respectively.

Key words: joint entity and relation extraction, multi-task learning, legal intelligence

王卓越, 陈彦光, 邢铁军, 孙媛媛, 杨亮, 林鸿飞. 基于多任务学习的多罪名案件信息联合抽取[J]. 计算机工程与应用, 2023, 59(2): 178-184.

WANG Zhuoyue, CHEN Yanguang, XING Tiejun, SUN Yuanyuan, YANG Liang, LIN Hongfei. Joint Entity and Relation Extraction for Multi-Crime Legal Documents with Multi-Task Learning[J]. Computer Engineering and Applications, 2023, 59(2): 178-184.

参考文献

[1] 中国裁判文书网[EB/OL].（2020-04-24）[2021-04-24].https：//wenshu.court.gov.cn/.
China judgements online[EB/OL].（2020-04-24）[2021-04-24].https：//wenshu.court.gov.cn/.
[2] MIWA M，BANSAL M.End-to-end relation extraction using LSTMs on sequences and tree structures[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics，Berlin，Germany，2016.
[3] ZHENG S C，WANG F，BAO H Y，et al.Joint extraction of entities and relations based on a novel tagging scheme[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics，Vancouver，Canada，2017：1227-1236.
[4] ZENG X R，ZENG D J，HE S Z，et al.Extracting relational facts by an end-to-end neural model with copy mechanism[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics，Melbourne，Australia，2018：506-514.
[5] ZENG D J，ZHANG H R，LIU Q Y.copymtl：copy mechanism for joint extraction of entities and relations with multi-task learning[C]//Proceedings of the 34th Conference on Artificial Intelligence，New York，USA，2020：9507-9514.
[6] NAYAK T，HWEE T N.Effective modeling of encoder-decoder architecture for joint entity and relation extraction[C]//Proceedings of the 34th Conference on Artificial Intelligence，New York，USA，2020：8528-8535.
[7] CHEN Y G，SUN Y Y，YANG Z H，et al.Joint entity and relation extraction for legal documents with legal feature enhancement[C]//Proceedings of the 28th International Conference on Computational Linguistics，Barcelona，Spain，2020：1561-1571.
[8] MISRA I，SHRIVASTAVA A，GUPTA A，et al.Cross-stitch networks for multi-task learning[C]//Proceedings of Computer Vision and Pattern Recognition，Las Vegas，NV，USA，2016：3994-4003.
[9] FELIX J S B，TANNO R，OURSELIN S，et al.Stochastic filter groups for multi-task CNNs：learning specialist and generalist convolution kernels[C]//Proceedings of International Conference on Computer Vision，Seoul，Korea（South），2019：1385-1394.
[10] VANDENHENDE S，GEORGOULIS S，PROESMANS M，et al.Revisiting multi-task learning in the deep learning era[EB/OL].（2020-04-28）[2021-06-24].https：//arxiv.org/abs/2004.13379.
[11] SGAARD A，GOLDBERG Y.Deep multi-task learning with low level tasks supervised at lower layers[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics，Berlin，Germany，2016.
[12] LIU P F，QIU X P，HUANG X J.Adversarial multi-task learning for text classification[J].arXiv：1704.05742，2017.
[13] XIAO L Q，ZHANG H L，CHEN W Q.Gated multi-task network for text classification[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics：Human Language Technologies，New Orleans，Louisiana，USA，2018：726-731.
[14] HASHIMOTO K，XIONG C M，TSURUOKA Y，et al.A joint many-task model：growing a neural network for multiple NLP tasks[C]//Proceedings of the Empirical Methods in Natural Language Processing，2017：1923-1933.
[15] SUN K，ZHANG R，MENSAH S，et al.Progressive multi-task learning with controlled information flow for joint entity and relation extraction[C]//Proceedings of the 35th Conference on Artificial Intelligence，2021：13851-13859.

[16] TANG H Y，LIU J N，ZHAO M，et al.Progressive layered extraction（PLE）：a novel multi-task learning（MTL） model for personalized recommendations[C]//Proceedings of RecSys’20：Fourteenth ACM Conference on Recommender Systems，2020：269-278.

[17] MIKOLOV T，CHEN K，CORRADO G，et al.Efficient estimation of word representations in vector space[C]//Proceedings of 1st International Conference on Learning Representations，Scottsdale，Arizona，USA，2013.