Giters

Doragd / Text-Classification-PyTorch

Implementation of papers for text classification task on SST-1/SST-2

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Why does the implementation worst than the paper report?

A11en0 opened this issue · comments

commented

For each dataset, your implementation worst than the paper about 2~4%? It's may be the database problem?

commented

Sorry for misleading you. The project is a toy example about text classification. I do not spend much time checking if the result of the original paper can be reproduced.