Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
AlphaUncommon

MenglinLu/Chinese-clinical-NER

CCKS2019中文命名实体识别任务。从医疗文本中识别疾病和诊断、解剖部位、影像检查、实验室检验、手术和药物6种命名实体。现已实现基于jieba和AC自动机的baseline构建、基于BiLSTM和CRF的序列标住模型构建。bert的部分代码主要源于https://github.com/charles9n/bert-sklearn.git 感谢作者。 模型最终测试集得分0.81,还有较大改进空间。可以当做一个baseline。

Owner
MenglinLu (personal account)
Stars
Stars: 351
Forks
Forks: 77
Language
Python
License
None
Created
2019
Tier
Alpha (250 to 699 ★) What this tier means
View on GitHub

More repos by MenglinLu

All 2 repos by MenglinLu

Nearby in Python

All Python repos