Abstract
As one of the important subtasks of legal judgment prediction, charge prediction aims to predict the final charge according to the fact description of a legal case. It can help make legal judgments or provide legal professional guidance for non-professionals. Most existing works focus on predicting charges only based on the fact description of a legal case while ignoring the semantic information of charge labels. Moreover, suffering from data imbalance in real applications, they are not applicable to predict few-shot charges by lack of training data. To address these issues, we propose a novel legal text presentation based on pre-trained model for charge prediction, named joint label-enhanced representation (JLER), which provides abundant information of charge labels as additional legal knowledge for pre-trained model to improve the charge prediction performance. JLER can improve predicting accuracy and interpretability by combining the charge label information enhanced by double-layer attention with legal text information, along with relieving the impact of data imbalance by fine-tuning pre-trained model from both text features side and charge label one. Experimental results on two real-world datasets demonstrate that our proposed model achieves significant and consistent improvements compared to the state-of-the-art baselines. Specifically, our model outperforms the baselines by about 13.9% accuracy on few-shot charge prediction. It is indicated that the proposed JLER model has good performance for charge prediction and is prospected to be applied to other subtasks of legal judgement prediction.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Nagel, S.S.: Applying correlation analysis to case prediction. Tex. l. Rev. 42(7), 1006–1017 (1964)
Segal, J.A.: Predicting supreme court cases probabilistically: the search and seizure cases, 1962–1981. Am. Political Sci. Rev. 78(4), 891–900 (1984)
Lauderdale, B.E., Clark, T.S.: The supreme court’s many median justices. Am. Political Sci. Rev. 106(4), 847–866 (2012)
Katz, D.M., Bommarito, M.J., Blackman, J.: A general approach for predicting the behavior of the supreme court of the United States. PLoS ONE 12(4), e0174698 (2017)
Hu, Z., Li, X., Tu, C., Liu, Z., Sun., M.: Few-shot charge prediction with discriminative legal attributes. In: Proceedings of the COLING (2018)
Zhong, H., Guo, Z., Tu, C.: Legal judgment prediction via topological learning. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3540–3549. Association for Computational Linguistics, Brussels, Belgium (2018)
Luo, B., Feng, Y., Xu, J., Zhang, X., Zhao, D.: Learning to predict charges for criminal cases with legal basis, pp. 2727–2736 (2017)
Shaghaghian, S., Feng, L.Y., Jafarpour, B., Pogrebnyakov, N.: Customizing contextualized language models for legal document reviews. In: Proceedings of the IEEE International Conference on Big Data (Big Data), pp. 2139–2148 (2020)
Shao, Y., et al.: BERT-PLI: modeling paragraph-level interactions for legal case retrieval. In: Proceedings of IJCAI, pp. 3501–3507 (2020)
Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. Ar**v abs/1907.11692 (2019)
Zhong, H., Zhang, Z., Liu, Z., Sun, M.: Open Chinese Language Pre-trained Model Zoo. Technical Report (2019)
Chalkidis, I., Fergadiotis, M., Malakasiotis, P., Aletras, N., Androutsopoulos, I.: LEGAL-BERT: “preparing the muppets for court”. In: Proceedings of EMNLP: Findings, pp. 2898–2904 (2020)
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL HLT, pp. 4171–4186 (2019)
**ao, C., et al.: CAIL2018: a large-scale legal dataset for judgment prediction. Ar**v abs/1807.02478 (2018)
Kim, Y.: Convolutional neural networks for sentence classification. EMNLP (2014)
Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manage. 24(5), 513–523 (1988)
Suykens, J.A., Vandewalle, J.: Least squares support vector machine classifiers. Neural Process. Lett. 9(3), 293–300 (1999)
Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 2048–2057 (2015)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. ar**v preprint ar**v:1412.6980 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dan, J., Liao, X., Xu, L., Hu, W., Zhang, T. (2022). A Joint Label-Enhanced Representation Based on Pre-trained Model for Charge Prediction. In: Lu, W., Huang, S., Hong, Y., Zhou, X. (eds) Natural Language Processing and Chinese Computing. NLPCC 2022. Lecture Notes in Computer Science(), vol 13551. Springer, Cham. https://doi.org/10.1007/978-3-031-17120-8_54
Download citation
DOI: https://doi.org/10.1007/978-3-031-17120-8_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17119-2
Online ISBN: 978-3-031-17120-8
eBook Packages: Computer ScienceComputer Science (R0)
