macanv / BERT-BiLSTM-CRF-NER

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
https://github.com/macanv/BERT-BiLSMT-CRF-NER
4.67k stars 1.25k forks source link

关于训练的输入 text_a 和 lable 的疑问。 #355

Open darelikz opened 4 years ago

darelikz commented 4 years ago

image

thu_classification.py 文件的代码中:

1、 def get_labels(self): 里面的lables 是 [ "[PAD]","B-MISC", "I-MISC", "O", "B-PER"]
还是 [["[PAD]","B-MISC", "I-MISC", "O", "B-PER"],[],[]]

2、 def _create_examples(self, lines, set_type) 中 ,text_a 是 句子? lable 是 一个标注,还是标注的集合?