MyungHa Kwon comments

Results 35 comments of


MyungHa Kwon

SAINT on Ednet data

Thanks for informing!

SAINT on Ednet data

@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...

SAINT on Ednet data

Sorry but I haven't measure metrics other than AUC so far.

suggestions and questions on training the data

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....

May I know the command line parameter when running LSTM_weight_tying(dim:100)

Just add --tying and set --r_emb, --r_l with same size. Sorry for bad README lol.

May I know the command line parameter when running LSTM_weight_tying(dim:100)

Depends on the dataset but 100 worked best on MovieLens 1M.

May I know the command line parameter when running LSTM_weight_tying(dim:100)

I didn't

Question on your paper.

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 +...

Question on your paper.

That's too bad for me. Thanks for the informing.

Question on your paper.

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...