Mastafa H Foufa
Hi, I tried that with the default dataset and with a custom dataset on both **Google chrome** and **Edge**. Indeed, when there is not much data points it works well...
Great @w4nderlust, indeed it is very likely to be Bokeh related. I find Bokeh not really optimal. Any idea **when** the next release is?
Hi @JasonKessler , I have the same issue here and I could not solve it with your suggestion. Basically, the following code is used: ```python data = data.loc[:, ['id', 'language',...
Works great @JasonKessler! Thanks 😄
Really interesting paper. Good job Bin! I will try to compare pre-trained models from UKPLab and your pretrained embeddings on WMT similarity task. From the README, I assume that I...
Hi @BinWang28 , how would you go to provide sentence-embeddings from your code? I checked **sen_emb.py** after looking at **example2.sh**, but I cannot see where is your pretrained model exactly?...
Hi @BinWang28 , are you planning on sharing multilingual models as well? That would be of interest for me.