bert+lstm+crf ner实体识别_bert + crf 实体识别 tensorflow

参考：
https://github.com/BrikerMan/Kashgari

https://eliyar.biz/nlp_chinese_text_classification_in_15mins/

bert预训练中文模型下载：百度云下载地址：https://pan.baidu.com/s/16JJp6NMCjmIT8PqP9OfN4g
包含这些内容的整体下载下来

!pip install kashgari

!pip install -i https://pypi.tuna.tsinghua.edu.cn/simple tensorflow==1.14

from kashgari.corpus import ChineseDailyNerCorpus

train_x, train_y = ChineseDailyNerCorpus.load_data('train')
valid_x, valid_y = ChineseDailyNerCorpus.load_data('validate')
test_x, test_y  = ChineseDailyNerCorpus.load_data('test')


print(f"train data count: {len(train_x)}")
print(f"validate data count: {len(valid_x)
1
2
3
4
5
6
7
8