Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
xiongying 1d1f15f582 | 1 year ago | |
---|---|---|
data | 2 years ago | |
layer | 2 years ago | |
model | 2 years ago | |
process_code | 2 years ago | |
utils | 2 years ago | |
.gitignore | 2 years ago | |
1.png | 2 years ago | |
1.txt | 2 years ago | |
README.en.md | 2 years ago | |
README.md | 1 year ago | |
infer.sh | 2 years ago | |
main.py | 2 years ago | |
meizhou1.txt | 2 years ago | |
meizhou2.txt | 2 years ago | |
meizhou3.txt | 2 years ago | |
meizhou4.txt | 2 years ago | |
meizhou5.txt | 2 years ago | |
meizhou_all.txt | 2 years ago | |
meizhou_dev.json | 2 years ago | |
run.sh | 2 years ago | |
run_ch.sh | 2 years ago | |
run_en.sh | 2 years ago | |
test.json | 2 years ago | |
test.py | 2 years ago | |
test.txt | 2 years ago | |
train.txt | 2 years ago |
knowledge-enhanced flat NER(named entity recognition)。对于中文则是引入知识图谱概念以及词典信息,对于英文可以引入知识图谱概念和短语信息。主要通过构建图来进行传递信息。
cudnn 9.2
python 3.6
pytorch 1.6.0
transformers 3.4.0
pytorch-pretrained-bert 0.6.2
# 文件
utils/config.py
# 具体一些设置
词典或者概念形式:
当为中文时,设置语言为“CN”,词语中的字和字之间没有操作,如“中国”
当为英文时或者西文时,设置语言为“EN”,概念或者短语的token之间用“&”分割,例如“bacteroides fragilis”在词典里为“bacteroides&fragilis”。
训练数据格式:
字符 label 起始位置 终止位置
主 O 0 1
因 O 2 4
腰 B-身体部位 5 9
部 I-身体部位 10 13
疼 B-症状和体征 14 17
痛 I-症状和体征 18 20
1 O 21 23
小 O 24 26
时 O 27 29
于 O 30 32
2016 O 33 35
每行用“\t”分隔,句子之间按照空行分隔开。
run.sh
infer.sh
Xiong Y, Peng H, Xiang Y, et al. Leveraging Multi-source knowledge for Chinese clinical named entity recognition via relational graph convolutional network[J]. Journal of Biomedical Informatics, 2022, 128: 104035.
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》