Costas Mavromatis

Hi! Unfortunately, I have not kept the trained model or the log files. However, I have the commands for reproducing the experiments [here](https://docs.google.com/document/d/194zIPtJdUxreMw7qXESR83aBXWI4kXPqOeWOPQeB_dg/edit), e.g., ``` python ./train_qa_model.py --model tempoqr --supervision...

Great question, we used the preprocessed files from NSM directly. I think you might be able to find the mapping from entity IDs to entity names based on these scripts:...

Hi, Thank you for your interest in our work. We use the incomplete KGs as processed in the [Graftnet](https://github.com/haitian-sun/GraftNet) repo; we downloaded the KGs from there.

As far as I recall, we performed hyper-parameter tuning for the incomplete KGs (I have not saved the log files). For MetaQA, please use `if i % 2 == 0:...