label of "[SEP]", "[PAD]" and "[CLS]"

kyzhouhzau / BERT-NER

Use Google's BERT for named entity recognition （CoNLL-2003 as the dataset）.

MIT License

1.23k stars 335 forks source link

Open congchan opened 5 years ago

congchan commented 5 years ago

The idea of not using the "[SEP]" in NER task seems great, but why it will cause problem in crf?

Per the "[CLS]", have you tried to replace it with "[PAD]"?

secsilm commented 4 years ago

I have trained ner model with my data and got pretty good result. Not even using [CLS].