Distinguish Confusion in Legal Judgment Prediction via Revised Relation Knowledge
Preprint
Abstract
Legal Judgment Prediction (LJP) aims to automatically predict a law case's judgment results based on the text description of its facts. In practice, the confusing law articles (or charges) problem frequently occurs, reflecting that the law cases applicable to similar articles (or charges) tend to be misjudged. Although some recent works based on prior knowledge solve this issue well, they ignore that confusion also occurs between law articles with a high posterior semantic similarity due to the data imbalance problem instead of only between the prior highly similar ones, which is this work's further finding. This paper proposes an end-to-end model named \textit{D-LADAN} to solve the above challenges. On the one hand, D-LADAN constructs a graph among law articles based on their text definition and proposes a graph distillation operation (GDO) to distinguish the ones with a high prior semantic similarity. On the other hand, D-LADAN presents a novel momentum-updated memory mechanism to dynamically sense the posterior similarity between law articles (or charges) and a weighted GDO to adaptively capture the distinctions for revising the inductive bias caused by the data imbalance problem. We perform extensive experiments to demonstrate that D-LADAN significantly outperforms state-of-the-art methods in accuracy and robustness.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Contrastive Learning for Legal Judgment PredictionACM Transactions on Information Systems, 2023
- Improving legal judgment prediction through reinforced criminal element extractionInformation Processing & Management, 2022
- Lawformer: A pre-trained language model for Chinese legal long documentsAI Open, 2021
- MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions2019
- Exploring the Semantic Content of Unsupervised Graph Embeddings: An Empirical StudyData Science and Engineering, 2019
- Deeper Insights Into Graph Convolutional Networks for Semi-Supervised LearningProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Legal Judgment Prediction via Topological Learning2018
- Learning to Predict Charges for Criminal Cases with Legal Basis2017
- Hierarchical Attention Networks for Document Classification2016
- Predicting Supreme Court Decisions Mathematically: A Quantitative Analysis of the “Right to Counsel” CasesAmerican Political Science Review, 1957