Solution for quora Quora question pairs challenge using pretrained BERT models
Steps to reproduce:
- Initialize git submodules
git submodule update --init --recursive - Make sure you have installed packages from requirements
- Download quora-pairs-dataset.zip and unzip it to
./data(create if missing) - Download checkpoint weights for models from google drive
model1 model2
and put them into
./models(create if missing)
Additionally, script was created to help you automate this, but in case it doesn't work for you just make above steps manually
Now, everything is ready. You may replicate the submission by running in Python
from utils import replicate
replicate(YOUR_PATH)which will create submission csv with specified path