Closed wjczf123 closed 4 years ago
BERT-PAIR for Domain Adaptation (FewRel 2.0) achieves 67.41 for 5-way 1-shot in the repository and website. But in your paper BERT-PAIR achieves 56.25 for 5-way 1-shot in your paper. Is there a discrepancy between paper and repository?
Hi, the results in the repo and the benchmark website are updated after further tuning the hyper-parameters. The method is exactly the same.
OK. Thank you a lot.
BERT-PAIR for Domain Adaptation (FewRel 2.0) achieves 67.41 for 5-way 1-shot in the repository and website. But in your paper BERT-PAIR achieves 56.25 for 5-way 1-shot in your paper. Is there a discrepancy between paper and repository?