Need help with KnowledgeGraph_NER?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

pumpkinduo
148 Stars 37 Forks 12 Commits 3 Opened issues

Description

中文医学知识图谱命名实体识别,包括bi-LSTM+CRF,transformer+CRF等模型

Services available

!
?

Need anything else?

Contributors list

No Data

medical_NER

本项目数据集来自ccks2017任务二,任务是中文病例的命名实体识别

数据处理后主要类标

"O" "B-body" "I-body" "E-body" "B-symp" "I-symp" "E-symp" "B-dise" "I-dise" "E-dise" "B-chec" "I-chec" "E-chec" "B-cure" "I-cure" "E-cure"

模型结构

采用bi-LSTM+CRF/transformer+CRF,此后会对模型进行优化,数据根据需求处理。
1.dataset文件夹 原始数据
2.LSTMCRF.py bi-LSTM模型
3.data
util.py 数据处理
4.train.py main
5.transformer_CRF transformer模型

Requirements

python 3
tensorflow 1.12

评价指标

microF1 打分函数precisionrecallfscore_support

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.