Tim Dettmers

I never tested my library with Windows and there seem to be some issues with that. Unfortunately, I do not have the time to look into this in detail. Would...

For 1-(0.1N) scoring, I hacked my code just to get some evaluation metrics. I will look into this and will see if it makes sense to integrate it into the...

One reason why I did not provide my code for this is that it is very messy and cannot be combine with my framework. The simplest solution might be to...

[Stackoverflow](https://stackoverflow.com/questions/35879096/pickle-unpicklingerror-could-not-find-mark) says that this error might happen if you open file somewhere else and do not reset it to its initial position. I, personally, have not seen this error. Another...

I have never tried it on Windows and do not know in which way git differs across these platforms. Please let me know if you run into any problems.

It is a bit surprising that DistMult is so large even though it scales linearly but the issue is that knowledge graphs can be large and it scales with the...

Yes, that is correct! I also tried to have an alternating, checker pattern between both embeddings which takes the idea to the extreme, but this did not help more than...

You create a folder with your dataset name. `ConvE/data/mydataset` and in that folder you have three files: `train.txt`, `valid.txt`, `test.txt`. These files have the format `e1\trel\te2` where `\t` is a...

This is something that was not really done well by me. There is no early stopping code. Instead what I do is I go through the logs and look at...

Thank you for the time writing this up. When I look at your calculation everything seems to be alright. There is one thing that you missed though, that is that...