Abstract
People unfamiliar with the law may not know what kind of behavior is considered criminal behavior or the lengths of sentences tied to those behaviors. This study used criminal judgments from the district court in Taiwan to predict the type of crime and sentence length that would be determined. This study pioneers using Taiwanese criminal judgments as a dataset and proposes improvements based on Bidirectional Encoder Representations from Transformers (BERT). This study is divided into two parts: criminal charges prediction and sentence prediction. Injury and public endangerment judgments were used as training data to predict sentences. This study also proposes an effective solution to BERT’s 512-token limit. The results show that using the BERT model to train Taiwanese criminal judgments is feasible. Accuracy reached 98.95% in predicting criminal charges and 72.37% in predicting the sentence in injury trials, and 80.93% in predicting the sentence in public endangerment trials.
Reference39 articles.
1. Extractive summarization of legal decisions using multi-task learning and maximal marginal relevance;Agarwal,2022
2. CyBERT: cybersecurity claim classification by fine-tuning the BERT language model;Ameri;Journal of Cybersecurity and Privacy,2021
3. Sparks of artificial general intelligence: early experiments with GPT-4;Bubeck,2019
4. Neural legal judgment prediction in English;Chalkidis,2019
5. Extreme multi-label legal text classification: a case study in EU legislation;Chalkidis,2019