A Novel Named Entity Recognition Approach of Judicial Case Texts Based on BiLSTM-CRF

The identification of named entity in judicial case texts is the critical phrase of knowledge graph information extraction in judicial fields. This paper proposes a neural network model based on bi-directional long-short term memoryconditional random field algorithm for the judicial case texts, named BiLSTM-CRF-JCT. Firstly, data preprocessing utilizes BIO notation to label sentences containing key named entities in judicial case texts, and then transfers sentences containing related entities into character vectors as input data. Afterward, the BiLSTM model is utilized to process vectors in order to obtain the sentence features. Finally, the proposed approach uses the CRF model to label and extract entities to realize named entity recognition. The experimental results show that the accuracy and recall rate of the proposed model are significantly improved compared with other NER algorithm models, F1 value is about 16% higher, which certifies that the BiLSTM-CRF-JCT model has good NER performance.