AI-secure / InfoBERT

[ICLR 2021] "InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective" by Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu
82 stars 7 forks source link

How are A1,A2, A3 scores calculated from r1,r2,r3 test results? #2

Closed ishanisri closed 3 years ago

ishanisri commented 3 years ago

The results of evaluation show here in the README file vs the ones in the paper are based on different metrics. The paper shows A1,A2,A3 scores along with accuracy on adv-MNLi, adv-SNLi etc, whereas running the evaluation here shows us accuracy roundwise of both tests and dev data. Is there any formula to calculate the A1,A2,A3 scores from the test scores mentioned in the repo?

Thanks in advance for the help :)

boxin-wbx commented 3 years ago

You may find A1, A2, A3 test scores in the log, which are respectively anli-r1-test, anli-r2-test, anli-r3-test.

ishanisri commented 3 years ago

Ah okay, this helped a lot, thanks!