longlongman / CasRel-pytorch-reimplement

Pytorch reimplement of the paper "A Novel Cascade Binary Tagging Framework for Relational Triple Extraction" ACL2020. The original code is written in keras.
200 stars 53 forks source link

请问模型里用到的BERT参与训练了么? #25

Open liyunhan opened 2 years ago

liyunhan commented 2 years ago

想请教您两个问题:

  1. 模型中的BERT参与到反向传播了么?还是说只当成Embedding用了呢?
  2. BERT的输入需要在句子头尾加入[cls]和[spe],如果我在BERT后面接入一个LSTM而不是Linear,那是不是要在BERT的输出中截断这两个位置的向量呢?