An External Knowledge Enhanced Multi-label Charge Prediction Approach with Label Number Learning
This work addresses the challenge of predicting multiple charges in legal cases, which is important for legal professionals, but it is incremental as it builds on existing deep learning models with enhancements.
The authors tackled the problem of multi-label charge prediction in legal cases by proposing an approach that automatically adjusts thresholds for label numbers using external knowledge from law provisions, resulting in improvements of 3%-5% in macro-F1 and 5%-15% in micro-F1 over baselines.
Multi-label charge prediction is a task to predict the corresponding accusations for legal cases, and recently becomes a hot topic. However, current studies use rough methods to deal with the label number. These methods manually set parameters to select label numbers, which has an effect in final prediction quality. We propose an external knowledge enhanced multi-label charge prediction approach that has two phases. One is charge label prediction phase with external knowledge from law provisions, the other one is number learning phase with a number learning network (NLN) designed. Our approach enhanced by external knowledge can automatically adjust the threshold to get label number of law cases. It combines the output probabilities of samples and their corresponding label numbers to get final prediction results. In experiments, our approach is connected to some state of-the art deep learning models. By testing on the biggest published Chinese law dataset, we find that our approach has improvements on these models. We future conduct experiments on multi-label samples from the dataset. In items of macro-F1, the improvement of baselines with our approach is 3%-5%; In items of micro-F1, the significant improvement of our approach is 5%-15%. The experiment results show the effectiveness our approach for multi-label charge prediction.