issues
search
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.
197
stars
52
forks
source link
看起来每个样本只是用了一个sub以及其对应的obj
#22
Open
scarydemon2
opened
2 years ago
scarydemon2
commented
2 years ago
为什么不把样本中所有sub拿出来用呢?这样训练数据能大很多
longlongman
commented
2 years ago
如果训练步数足够多,那基本上每个sub都会被采样到的
为什么不把样本中所有sub拿出来用呢?这样训练数据能大很多