search

allenai / commonsense-kg-completion

MIT License
105 stars 16 forks source link

Ablations for non commensense KGs and BERT? #15

Open nishanthcgit opened 2 years ago

nishanthcgit commented 2 years ago

Hi, I really liked the paper and the approaches outlined. I had two questions:

  1. I know the paper is targeted towards commonsense KGs, but are there results for this technique on standard KG benchmark datasets like WN18/FB15k-237/the RR versions?
  2. Are there any ablations to show the effect of BERT pretraining? (fine tuning with MLM on the corpus used in the nodes vs using a standard off the shelf pretrained BERT)