Belinkov, YonatanPoliak, AdamShieber, StuartVan Durme, BenjaminRush, Alexander Sasha2019-07-032019-06Belinkov, Yonatan, Adam Poliak, Stuart M. Shieber, Benjamin Van Durme, and Alexander Rush. 2019. On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference. In the Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM19), Minneapolis, MN, June 6-7, 2019.http://nrs.harvard.edu/urn-3:HUL.InstRepos:40827358Popular Natural Language Inference (NLI) datasets have been shown to be tainted by hypothesis-only biases. Adversarial learning may help models ignore sensitive biases and spurious correlations in data. We evaluate whether adversarial learning can be used in NLI to encourage models to learn representa- tions free of hypothesis-only biases. Our analyses indicate that the representations learned via adversarial learning may be less biased, with only small drops in NLI accuracy.en-USConference Paper2019-07-03