Castor

mirror of https://github.com/wassname/Castor.git synced 2026-09-25 13:10:11 +08:00

Files

T

+ cleaned up the model code for the simple qa directory
+ created vocab objects for pre-loading word embeddings easily

2017-06-19 14:24:27 -04:00

2017-06-19 14:24:27 -04:00

2017-06-19 14:24:27 -04:00

.gitignore

2017-06-19 14:24:27 -04:00

args.py

2017-06-19 14:24:27 -04:00

fetch_and_preprocess.sh

2017-06-19 14:24:27 -04:00

hyperparameter_tuning.py

2017-06-19 14:24:27 -04:00

README.md

2017-06-19 14:24:27 -04:00

relation_model.py

2017-06-19 14:24:27 -04:00

relation_prediction_results.txt

2017-06-19 14:24:27 -04:00

train_relation_model.py

2017-06-19 14:24:27 -04:00

Directions:

Download SimpleQuestions data from this link and put it in directory "data/SimpleQuestions_v2/"
Run this script to download GloVe word embeddings and do some preprocessing.

bash fetch_and_preprocess.sh

Run this command to train the model. Make sure you have PyTorch and other Python dependencies installed.

python train_relation_model.py

For GPU, use:

python train_relation_model.py --cuda