joelxiangnanchen issues

Repositories
Issues
Comments

Results 3 issues of


                                            joelxiangnanchen

Is there any compressive transformers pre-trained model releasing plan?

Hi, thx for your guys' great works. Is there any compressive transformers pre-trained model releasing plan? Want to see CT as backbone of GPT2 or BERT on long document like...

predict linear layer's input is just hidden states but in original paper, they combined with [L(word_embed+Wh+Uc)]

Hi, Thx for your great tutorial with nice guide and code. After I read decoder's code, I found that you just use lstm's hidden states to compute the next word's...

Is there any pretrained "conpono" model release plan?

RT. thx for your nice work to enhance BERT with discourse awareness!