When Choosing Plausible Alternatives, Clever Hans can be Clever

Pride Kavumba, Naoya Inoue, Benjamin Heinzerling, Keshav Singh, Paul Reisert, Kentaro Inui


Abstract
Pretrained language models, such as BERT and RoBERTa, have shown large improvements in the commonsense reasoning benchmark COPA. However, recent work found that many improvements in benchmarks of natural language understanding are not due to models learning the task, but due to their increasing ability to exploit superficial cues, such as tokens that occur more often in the correct answer than the wrong one. Are BERT’s and RoBERTa’s good performance on COPA also caused by this? We find superficial cues in COPA, as well as evidence that BERT exploits these cues. To remedy this problem, we introduce Balanced COPA, an extension of COPA that does not suffer from easy-to-exploit single token cues. We analyze BERT’s and RoBERTa’s performance on original and Balanced COPA, finding that BERT relies on superficial cues when they are present, but still achieves comparable performance once they are made ineffective, suggesting that BERT learns the task to a certain degree when forced to. In contrast, RoBERTa does not appear to rely on superficial cues.
Anthology ID:
D19-6004
Volume:
Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Simon Ostermann, Sheng Zhang, Michael Roth, Peter Clark
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
33–42
Language:
URL:
https://aclanthology.org/D19-6004
DOI:
10.18653/v1/D19-6004
Bibkey:
Cite (ACL):
Pride Kavumba, Naoya Inoue, Benjamin Heinzerling, Keshav Singh, Paul Reisert, and Kentaro Inui. 2019. When Choosing Plausible Alternatives, Clever Hans can be Clever. In Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing, pages 33–42, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
When Choosing Plausible Alternatives, Clever Hans can be Clever (Kavumba et al., 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/D19-6004.pdf
Data
COPA