I have set up training with most default params on a very small dataset so that it is easier to get started. Just running the script should work.
/bin/bash run.sh ./config.sh
The processed data (train/dev/test split) is stored in dataformatted/ directory. To download the KB files used for the project run, ``` sh getdata.sh ``` After downloading the data, you will have to change the appropriate entries in the config.sh file (kbfile and textkb_file).
The embeddings used for initializing the network can be downloaded from here
We are also releasing the output predictions of our model for comparison. Find them in the model_outputs directory.
We are also sharing our pretrained model. Get it here. The following will load the model and get the answers from the dev set. Please change the config appropriately.
sh run.sh ./test_from_saved_model.sh