Adversarial NLI: A New Benchmark for Natural Language Understanding

Yixin Nie, Adina Williams, Emily Dinan, Mohit Bansal, Jason Weston, Douwe Kiela


Abstract
We introduce a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure. We show that training models on this new dataset leads to state-of-the-art performance on a variety of popular NLI benchmarks, while posing a more difficult challenge with its new test set. Our analysis sheds light on the shortcomings of current state-of-the-art models, and shows that non-expert annotators are successful at finding their weaknesses. The data collection method can be applied in a never-ending learning scenario, becoming a moving target for NLU, rather than a static benchmark that will quickly saturate.
Anthology ID:
2020.acl-main.441
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4885–4901
Language:
URL:
https://aclanthology.org/2020.acl-main.441
DOI:
10.18653/v1/2020.acl-main.441
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.441.pdf
Video:
 http://slideslive.com/38928732