Don’t Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference

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


Abstract
Natural Language Inference (NLI) datasets often contain hypothesis-only biases—artifacts that allow models to achieve non-trivial performance without learning whether a premise entails a hypothesis. We propose two probabilistic methods to build models that are more robust to such biases and better transfer across datasets. In contrast to standard approaches to NLI, our methods predict the probability of a premise given a hypothesis and NLI label, discouraging models from ignoring the premise. We evaluate our methods on synthetic and existing NLI datasets by training on datasets containing biases and testing on datasets containing no (or different) hypothesis-only biases. Our results indicate that these methods can make NLI models more robust to dataset-specific artifacts, transferring better than a baseline architecture in 9 out of 12 NLI datasets. Additionally, we provide an extensive analysis of the interplay of our methods with known biases in NLI datasets, as well as the effects of encouraging models to ignore biases and fine-tuning on target datasets.
Anthology ID:
P19-1084
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
877–891
Language:
URL:
https://www.aclweb.org/anthology/P19-1084
DOI:
10.18653/v1/P19-1084
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/P19-1084.pdf
Presentation:
 P19-1084.Presentation.pdf
Video:
 https://vimeo.com/384034160