This project is the implementation of the paper Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks (IJCAI 2018)
- python2.7
- pytorch
- sacred
- torchtext 0.1.1
Please download glove.6B.100d.txt
and put into embed
folder.
# Train simple classifier with attention using sentiment dataset on gpu 0
python main.py with data_set='product/sentiment' use_model='SingleAttn' device=0 adversarial=False ex_name='experiment'
- Arguments
- use_model
- model architecture used for training
- use_model
To be continued ...