计算机科学
命名实体识别
嵌入
词典
人工智能
实体链接
自然语言处理
情报检索
知识库
经济
管理
任务(项目管理)
作者
Qing Cong,Zhiyong Feng,Guozheng Rao,Li Zhang
标识
DOI:10.1007/978-3-031-30678-5_24
摘要
Medical named entity recognition can assist doctors to quickly identifying key content and improving clinical work efficiency. Chinese named entity recognition methods based on pre-trained language models have achieved remarkable performance. However, most of these models have the following problems for medical named entity recognition: these models are designed for flat named entity recognition tasks but not for nested entities. Furthermore, the medical entities are hard to be recognized due to the lack of medical domain knowledge. To tackle these problems, we propose a Chinese medical nested named entity recognition model based on feature fusion and a bidirectional lattice embedding graph. The problem of poor recognition of medical entities due to the lack of medical domain knowledge is solved by introducing a medical lexicon. The problem of Chinese polyphonic characters with different meanings in the same form is solved by introducing pinyin information. The model considers the similarity between different entity types to improve the model’s effectiveness. The results on a Chinese medical nested named entity dataset CBLUE-CMeEE demonstrate the outperform performance and effectiveness of the model.
科研通智能强力驱动
Strongly Powered by AbleSci AI