Abstract
Named entity recognition (NER) plays an essential role in natural language processing systems. Judicial NER is a fundamental component of judicial information retrieval, entity relation extraction, and knowledge map building. However, Chinese judicial NER remains to be more challenging due to the characteristics of Chinese and high accuracy requirements in the judicial filed. Thus, in this paper, we propose a deep learning-based method named BiLSTM-CRF which consists of bi-directional long short-term memory (BiLSTM) and conditional random fields (CRF). For further accuracy promotion, we propose to use Adaptive moment estimation (Adam) for optimization of the model. To validate our method, we perform experiments on judgment documents including commutation, parole and temporary service outside prison, which is acquired from China Judgments Online. Experimental results achieve the accuracy of 0.876, recall of 0.856 and F1 score of 0.855, which suggests the superiority of the proposed BiLSTM-CRF with Adam optimizer.
Highlights
With the development of the judicial online systems, a large amount of judicial data of various kinds of cases and documents have been accumulated
F1 = 2 × precision × recall precison + recall where true positive (TP) denotes the number of judicial named entities which are recognized and match the ground truth, while false positive (FP) means the number of characters which are recognized as named entity but do not match the ground truth, and false negative (FN) represents the number of characters that are annotated as ground truth but are not recognized but our model
We conducted a series of experiments using bi-directional long short-term memory (BiLSTM)-conditional random fields (CRF) with the three most prevailing optimizers: Adaptive moment estimation (Adam), GD and RMSprop
Summary
With the development of the judicial online systems, a large amount of judicial data of various kinds of cases and documents have been accumulated. How to give full play to the judicial data has become a hot topic of concern. Natural language processing (NLP) is a sensible way to deal with the data, of which named entity recognition (NER) is an indispensable subtask [1]. NER task is composed of two parts: detecting the entity boundaries and classifying the entities into predefined categories such as Name, Judicial Organization, and Location [2]. Chinese judicial NER can reduce the heavy burdens of related staff, improve the efficiency of the judicial industry, and help achieve information sharing. Judicial entities are mostly nested, making structures complicated, e.g. All these factors conspire Chinese judicial NER towards a challenging task
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
