Named Entity Recognition Method of Brazilian Legal Text based on pre-training model
Autor: | Yufan Wu, Cheng Peng, Pengbin Lei, Zhili Wang |
---|---|
Rok vydání: | 2020 |
Předmět: |
History
Sequence Basis (linear algebra) Computer science business.industry Convolution (computer science) computer.software_genre Sequence labeling Computer Science Applications Education Task (computing) Named-entity recognition Scalability Artificial intelligence F1 score business computer Natural language processing |
Zdroj: | Journal of Physics: Conference Series. 1550:032149 |
ISSN: | 1742-6596 1742-6588 |
Popis: | Named entity recognition (NER) is a common task in Natural Language Processing (NLP). To this end, we propose a novel approach based on pre-training model to complete the sequence labeling tasks by learning the large-scale real-world data from Brazilian legal documents. Especially, combining iterated dilated convolution[1] (IDCNN) and Bi-LSTM, we develop the scalable sequence labeling model named Sequence Tagging Model (STM) and extensive experiments validate the effectiveness of STM for NER tasks. Furthermore, compared with the IDCNN-CRF model, the experimental results show that the STM is better and the F1 score is 93.23%, which provides an important basis for NER tasks. |
Databáze: | OpenAIRE |
Externí odkaz: |