CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense

Michael Chen, Mike D’Arcy, Alisa Liu, Jared Fernandez, Doug Downey


Abstract
Commonsense reasoning is a critical AI capability, but it is difficult to construct challenging datasets that test common sense. Recent neural question answering systems, based on large pre-trained models of language, have already achieved near-human-level performance on commonsense knowledge benchmarks. These systems do not possess human-level common sense, but are able to exploit limitations of the datasets to achieve human-level scores. We introduce the CODAH dataset, an adversarially-constructed evaluation dataset for testing common sense. CODAH forms a challenging extension to the recently-proposed SWAG dataset, which tests commonsense knowledge using sentence-completion questions that describe situations observed in video. To produce a more difficult dataset, we introduce a novel procedure for question acquisition in which workers author questions designed to target weaknesses of state-of-the-art neural question answering systems. Workers are rewarded for submissions that models fail to answer correctly both before and after fine-tuning (in cross-validation). We create 2.8k questions via this procedure and evaluate the performance of multiple state-of-the-art question answering systems on our dataset. We observe a significant gap between human performance, which is 95.3%, and the performance of the best baseline accuracy of 65.3% by the OpenAI GPT model.
Anthology ID:
W19-2008
Volume:
Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP
Month:
June
Year:
2019
Address:
Minneapolis, USA
Venues:
NAACL | RepEval | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
63–69
Language:
URL:
https://www.aclweb.org/anthology/W19-2008
DOI:
10.18653/v1/W19-2008
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W19-2008.pdf