MyungHa Kwon
MyungHa Kwon
Thanks for informing!
@Nino-SEGALA Have you tried applying Noam scheme learning rate scheduling mentioned on the paper? It's in Training Details section. I got the same problem where auc stays around 0.5 with...
Sorry but I haven't measure metrics other than AUC so far.
1. Thanks for informing. I guess I have tried different batch sizes but I'm not sure how large I have tried. Batch size depends on the memory size of GPU....
Just add --tying and set --r_emb, --r_l with same size. Sorry for bad README lol.
Depends on the dataset but 100 worked best on MovieLens 1M.
I see. Parsing edges and predicting dependency labels are separate process. But If you used parse edges from Dozat and Manning's work, I thought it is corresponding to LISA +...
That's too bad for me. Thanks for the informing.
And I think you got my comment that is not up to date via e-mail. Maybe I should have added comment instead of modifying comment. Could you explain me the...