search

Rain9876 / Unsupervised-crosslingual-Compound-Method-For-MT

3 stars 1 forks source link

wmt17 dataset #2

Open Aureole-1210 opened 2 years ago

Aureole-1210 commented 2 years ago

I have found that the webpage for segment-level metrics data of wmt17 can't be opened yet. Could you please give me other link about it? More appreciate it!

Rain9876 commented 2 years ago

I've put the WMT17 data in the repo. But double-checking this is what you need.

Hope it helps.

MMMmmm @.***> 于2022年6月10日周五 21:06写道：

I have found that the webpage for segment-level metrics data of wmt17 can't be opened yet. Could you please give me other link about it? More appreciate it!

— Reply to this email directly, view it on GitHub https://github.com/Rain9876/Unsupervised-crosslingual-Compound-Method-For-MT/issues/2, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFQCHUS35JS4XYCQKGVVLYTVOM4U3ANCNFSM5YNT2ZHA . You are receiving this because you are subscribed to this thread.Message ID: <Rain9876/Unsupervised-crosslingual-Compound-Method-For-MT/issues/2@ github.com>

Aureole-1210 commented 2 years ago

I've put the WMT17 data in the repo. But double-checking this is what you need. Hope it helps. MMMmmm @.***> 于2022年6月10日周五 21:06写道： …

Thanks again for your help!!

Aureole-1210 commented 2 years ago

I still have a question. The paper mentioned "Each language has 560 sentence tuples". But the dataset contains far more than 560 sentence tuples for each language. Are the 560 sentence tuples for each language randomly sampled from the dataset? Thanks a lot!