Closed pyupya closed 4 years ago
Hey @pyupya I'm having the same issue as yours, did you manage to feed MetaQA dataset to this model?
I'm trying to use MetaQA on it, but didn't apply it yet.
2019년 12월 23일 (월) 오후 4:25, Saed Rezayi notifications@github.com님이 작성:
Hey @pyupya https://github.com/pyupya I'm having the same issue as yours, did you manage to feed MetaQA dataset to this model?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/OceanskySun/GraftNet/issues/10?email_source=notifications&email_token=AH7WCIDI3KBWEUFOWYVT3KLQ2BRVFA5CNFSM4JJCHLJ2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEHQNXKY#issuecomment-568384427, or unsubscribe https://github.com/notifications/unsubscribe-auth/AH7WCIDL522H56Q37DVDQITQ2BRVFANCNFSM4JJCHLJQ .
Hi,
The number for running GRAFT-Net on MetaQA is available here: https://arxiv.org/abs/1904.09537. I am working on open sourcing the pre-processed MetaQA data as well. Hope it helps.
Thanks, Haitian
The code for preprocessing on the WikiMovies dataset is now included in the wikimovie_preprocessing
subdirectory.
Hello, I'm studying with your code, really thanks to your code. I want to train and test more hops with 'MetaQA' dataset. It's made of wikiMovies, so I think have to preprocess it like wikiMovies. If you don't mind me asking, can I get preprocess codes for wikiMovies or MetaQA?
one more thing, how can I get document for dataset? Just I can get it from wikipedia, or can get from other source?
sorry for rude, thanks!