Pre-training language model

tricktreat / locate-and-label

Code for "Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition", accepted at ACL 2021.

102 stars 18 forks source link

Pre-training language model #10

Closed zongxindu closed 2 years ago

zongxindu commented 2 years ago

I was really inspired by your insight into nested entity recognition, but I have a question: why didn't the paper try to use a large pre-training model(BERT) as token presentation?