基于BERT的命名实体识别模型设计

Design of TCM Based on BERT Named Entity Recognition Method

针对传统命名实体识别方法不适用于中医领域,提出一种适用于中医领域的命名实体识别方法。在医古文数据集上的结果证明,所提出的模型有效提升模型的整体性能。

Aiming at the fact that the traditional named entity recognition method is not suitable for the field of traditional Chinese medicine, a named entity recognition model suitable for the field of traditional Chinese medicine is proposed in this paper. The results on the ancient medical text dataset prove that the proposed method can effectively solve the polysemy problem.