1. Research on Legal Judgment Prediction Based on Bert and LSTM-CNN Fusion Model
- Author
-
Lei Liu, Cao Jiang, Xuejie Ma, Yanxu Wang, and Dezhi An
- Subjects
Computer science ,business.industry ,Deep learning ,Machine learning ,computer.software_genre ,Filter (software) ,Legal judgment ,Field (computer science) ,Task (project management) ,Verdict ,Task analysis ,Artificial intelligence ,business ,computer - Abstract
In recent years, artificial intelligence has been advancing and intelligence in the judicial field has been developing, and legal Judgment prediction based on legal documents has become a hot research direction. The task of legal verdict prediction is to analyze the factual descriptions of real cases and mine the textual features in the factual descriptions. Most of the present-day legal verdict prediction uses deep learning methods, but its accuracy rate still needs to be improved. In this paper, we propose a fusion model based on Bert and LSTM-CNN for prediction, and use part of the datasets from the "China Law Research Cup" Judicial Artificial Intelligence Challenge to filter and conduct experiments. The experimental results show that compared with other common models, the proposed model has more accurate prediction results and achieves better standards in model evaluation criteria.
- Published
- 2021