- Python (developed on 3.5.2. Issues have been reported with Python 2!)
- tensorflow (deep learning library, verified on r0.11)
- nltk (NLP tools, verified on 3.2.1)
- tqdm (progress bar, verified on 4.7.4)
run_prep.sh <run name> calls an internal script (
zeroshot2squad.py) that changes our tab-delimited format to SQuAD's JSON format. It then performs any necessary preprocessing for the BiDAF model.
run_train.sh <run name> runs the training procedure.
run_test.sh <run name> runs the testing procedure, and yields an answer file in
python analyze.py <test set> <answer file> reads the test set and the model's answers, and returns the F1 score broken down by different factors.