Efficient Named Entity Recognition Based on Broad Learning System and BERT

In this paper, we propose an efficient approach for named entity recognition (NER). This paper applies the broad learning system (BLS) to NER task, which includes the feature learning and incremental learning processes. In the feature learning of BLS, the calculation of each new feature node involves only matrix multiplication, and can effectively reduce the amount of calculation to improve efficiency in obtaining rich features. In the incremental learning of BLS, the feature nodes are calculated by active function and ridge regression in order to obtain incremental nodes. In this paper, we combine the BLS with bidirectional encoder representations from transformers (BERT) and conditional random fields (CRF) algorithms to conduct NER of English corpus. Firstly, we extract features through BERT. Secondly, we use BLS to calculate the extracted features. Finally, we apply CRF to decoding features. In numerical experiments, NER of English corpus based on BIO schema is used as benchmark, And the proposed method shows higher accuracy and faster training than other baseline methods.