On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference

Yonatan Belinkov, Adam Poliak, Stuart Shieber, Benjamin Van Durme, Alexander Rush


Abstract
Popular 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 representations 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.
Anthology ID:
S19-1028
Volume:
Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Rada Mihalcea, Ekaterina Shutova, Lun-Wei Ku, Kilian Evang, Soujanya Poria
Venue:
*SEM
SIGs:
SIGSEM | SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
256–262
Language:
URL:
https://aclanthology.org/S19-1028
DOI:
10.18653/v1/S19-1028
Bibkey:
Cite (ACL):
Yonatan Belinkov, Adam Poliak, Stuart Shieber, Benjamin Van Durme, and Alexander Rush. 2019. On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference. In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), pages 256–262, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference (Belinkov et al., *SEM 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/S19-1028.pdf
Code
 azpoliak/robust-nli
Data
SNLI