A Named Entity Recognition Method Based on Deep Learning For Chinese Legal Documents
Jianwei Shi, Kai Zheng, Zhihua Zhang, Qi Liu · 2022 7th International Conference on Image, Vision and Computing (ICIVC) · 2022
As a fundamental task in information extraction, named entity recognition (NER) has received constant research attention over the recent years. Aiming at the NER of specific cause of action in the legal field, we summarize the key points in current legal documents, establish the corpus dataset of specific cause of action. Based on this dataset, we propose RoBERTa-BiLSTM-CRF legal case entity recognition model to improve the performance of Chinese legal NER. We compare the final experimental results and analyze the advantages and disadvantages of the model. Experimental results shows that our model achieves significant effect on legal NER.