# Generalization in NLI: Ways to [Not] Go Beyond Simple Heuristics

Published in Workshop on Insights from Negative Results, EMNLP 2021, 2021

Abstract: Much of recent progress in NLU was shown to be due to models’ learning dataset-specific heuristics. We conduct a case study of generalization in NLI (from MNLI to the adversarially constructed HANS dataset) in a range of BERT-based architectures (adapters, Siamese Transformers, HEX debiasing), as well as with subsampling the data and increasing the model size. We report 2 successful and 3 unsuccessful strategies, all providing insights into how Transformer-based models learn to generalize.

Citation

@misc{bhargava2021generalization,
title={Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics},
author={Prajjwal Bhargava and Aleksandr Drozd and Anna Rogers},
year={2021},
eprint={2110.01518},
archivePrefix={arXiv},
primaryClass={cs.CL}
}