1 code implementation • 5 Nov 2022 • Zihui Gu, Ju Fan, Nan Tang, Preslav Nakov, Xiaoman Zhao, Xiaoyong Du
In particular, on the complex set of TabFact, which contains multiple operations, PASTA largely outperforms the previous state of the art by 4. 7 points (85. 6% vs. 80. 9%), and the gap between PASTA and human performance on the small TabFact test set is narrowed to just 1. 5 points (90. 6% vs. 92. 1%).
Ranked #2 on Table-based Fact Verification on TabFact