Abstract
Legal judgment elements extraction (LJEE) aims to identify the different judgment features from the fact description in legal documents automatically, which helps to improve the accuracy and interpretability of the judgment results. In real court rulings, judges usually need to scan both the fact descriptions and the law articles repeatedly to find out the relevant information, and it is hard to acquire the key judgment features quickly, so legal judgment elements extraction is a crucial and challenging task for legal judgment prediction. However, most existing methods follow the text classification framework, which fails to model the attentive relations of the law articles and the legal judgment elements. To address this issue, we simulate the working process of human judges, and propose a legal judgment elements extraction method with a law article-aware mechanism, which captures the complex semantic correlations of the law article and the legal judgment elements. Experimental results show that our proposed method achieves significant improvements than other state-of-the-art baselines on the element recognition task dataset. Compared with the BERT-CNN model, the proposed “All labels Law Articles Embedding Model (ALEM)” improves the accuracy, recall, and F1 value by 0.5, 1.4 and 1.0, respectively.
- [1] . 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT. 4171–4186.Google Scholar
- [2] . 2014. Convolutional neural networks for sentence classification. In Proceedings of EMNLP. 1746–1751.Google Scholar
Cross Ref
- [3] . 1957. Predicting Supreme Court decisions mathematically: A quantitative analysis of the “right to counsel” cases. American Political Science Review 51, 1 (1957), 1–12.Google Scholar
Cross Ref
- [4] . 1963. Applying correlation analysis to case prediction. Texas Law Review 42, 106.Google Scholar
- [5] . 1963. Quantitative analysis of judicial processes: Some practical and theoretical applications. Law and Contemporary Problems, 164–184.Google Scholar
- [6] . 1999. Judicial policymaking in published and unpublished decisions: The case of environmental civil ligaton. Political Research Quarterly 52, 1 (1999), 7–37.Google Scholar
- [7] . 2012. Tom Clark: The Supreme Court's many median justices. American Political Science Review. 106, 4 (2012), 847–866.Google Scholar
Cross Ref
- [8] . 2018. Few-shot charge prediction with discriminative legal attributes. In Proceedings of the 27th International Conference on Computational Linguistics. 487–498.Google Scholar
- [9] . 2015. Predicting associated statutes for legal problems. Information Processing & Management 51, 1 (2015), 194–211.Google Scholar
Cross Ref
- [10] . 2019. Applying data discretization to DPCNN for law article prediction. In Proceedings of NLPCC. 459–470.Google Scholar
Digital Library
- [11] . 2018. Automatic judgment prediction via legal reading comprehension. arXiv preprint arXiv:1809.06537v1.Google Scholar
- [12] . 2018. Legal judgment prediction via topological learning. In Proceedings of EMNLP. 3540–3549.Google Scholar
Cross Ref
- [13] . 2019. Legal judgment prediction via multi-perspective bi-feedback network. In Proceedings of IJCAI. 4085–4091. Google Scholar
Digital Library
- [14] . 2019. A recurrent attention network for judgment prediction. In Proceedings of the ICANN. 253–266.Google Scholar
Digital Library
- [15] . 2020. How does NLP benefit legal system: A summary of legal artificial intelligence. In Proceedings of ACL (2020).Google Scholar
Cross Ref
- [16] . 2016. The mythos of model interpretability. arXiv preprint arXiv:1606.03490.Google Scholar
- [17] . 2016. Generating visual explanations. European Conference on Computer Vision. Springer, Cham, 2016: 3–19.Google Scholar
- [18] . 2016. Rationalizing neural predictions. arXiv preprint arXiv:1606.04155.Google Scholar
- [19] . 2018. Tree-enhanced embedding model for explainable recommendation. Proceedings of the 2018 World Wide Web Conference. International World Wide Web Conferences Steering Committee, 2018: 1543–1552. Google Scholar
Digital Library
- [20] . 2015. Interactive and interpretable machine learning models for human machine collaboration. Massachusetts Institute of Technology.Google Scholar
- [21] . 2004. PCA-based feature transformation for classification: Issues in medical diagnostics. Proceedings. 17th IEEE Symposium on Computer-Based Medical Systems. IEEE, 2004: 535–540. Google Scholar
Digital Library
- [22] . 2020. Iteratively questioning and answering for interpretable legal judgment prediction. In Proceedings of AAAI (2020).Google Scholar
Cross Ref
- [23] . 2017. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big Data, 5, 2 (2017), 153–163.Google Scholar
Cross Ref
- [24] . 2017. Legal NERC with ontologies, Wikipedia and curriculum learning. In Proceedings of EACL (2017).Google Scholar
Cross Ref
- [25] . 2017. A low-cost, high-coverage legal named entity recognizer, classifier and linker. In Proceedings of EACL (2017). Google Scholar
Digital Library
- [26] . 2018. Deep learning for named-entity linking with transfer learning for legal documents. In Proceedings of AICCC (2018). Google Scholar
Digital Library
- [27] . 2018. Neural entity reasoner for global consistency in named entity recognition. arXiv preprint arXiv:1810.00347v1.Google Scholar
- [28] . 2017. Event identification as a decision process with non-linear representation of text. In Proceedings of IIPV (2017).Google Scholar
- [29] . 2019. Apply event extraction techniques to the judicial field. The 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 492–497. Google Scholar
Digital Library
- [30] . 2011. Natural language processing (almost) from scratch. In Proceedings of JMLR. 2493–2537. Google Scholar
Digital Library
- [31] . 2014. A convolutional neural network for modelling sentences. In Proceedings of ACL. 655–665.Google Scholar
Cross Ref
- [32] . 2017. Combining knowledge with deep convolutional neural networks for short text classification, In Proceedings of IJCAI. 2915–2921. Google Scholar
Digital Library
- [33] . 2014. Effective use of word order for text categorization with convolutional neural networks. arXiv preprint arXiv:1412.1058.Google Scholar
- [34] . 2016. Efficient character-level document classification by combining convolution and recurrent layers. arXiv preprint arXiv:1602.00367.Google Scholar
- [35] . 2019. DocBERT: BERT for Document Classification. arXiv preprint arXiv:1904.08398v1.Google Scholar
- [36] . 1997. Long short-term memory. Neural Computation 9, 8 (1997), 1735–1780. Google Scholar
Digital Library
- [37] . 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.Google Scholar
Index Terms
Legal Judgment Elements Extraction Approach with Law Article-aware Mechanism
Recommendations
NeurJudge: A Circumstance-aware Neural Framework for Legal Judgment Prediction
SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information RetrievalLegal Judgment Prediction is a fundamental task in legal intelligence of the civil law system, which aims to automatically predict the judgment results of multiple subtasks, such as charge, law article, and term of penalty prediction. Existing studies ...
ML-LJP: Multi-Law Aware Legal Judgment Prediction
SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information RetrievalLegal judgment prediction (LJP) is a significant task in legal intelligence, which aims to assist the judges and determine the judgment result based on the case's fact description. The judgment result consists of law articles, charge, and prison term. ...
Review on Intelligent Processing Technologies of Legal Documents
Artificial Intelligence and SecurityAbstractDue to the imbalance between a large number of litigation cases and the number of judicial personnel, many legal documents to be processed greatly increase the burden of legal practitioners. So the intelligent processing of legal documents is ...






Comments