Phong Le

Thanks for letting me know. Let me fix it. In the mean time, if you are interested in only local local mode, you might want to have a look at...

I wasn't able to replicate their paper in the beginning. But then reading their source code https://github.com/dalab/deep-ed was super helpful.

You are right the if the number of relation is set to 1, we will have their model. Yes, I successfully replicated their results (even got a bit higher scores,...

Unfortunately, I don't have a facility to run the code. When you ran the command line in the README `python -u -m nel.main --mode train --n_rels 3 --mulrel_type ment-norm --model_path...

The reason for trying "rel-norm" instead of "ment-norm" is that for ment-norm the model uses mention padding, which Genea model doesn't have.

Hmm, could you please send me the log files (or what you get when running the cmd)?

Yes, please send to my gmail address (I no longer use UoEdin email address). Thanks!

Yes, I found the issue, but we had a private discussion which is not shown here. Long story short, lej-la commented out an important line. Could you show your log...

okay, so they differ at the normalization factor. Thanks for pointing out

Hi. It is unfortunate that the source code is not for testing on input raw texts. There are quite several preprocessing steps to make it work this case, but I'm...