Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding

Shane Storks, Qiaozi Gao, Yichi Zhang, Joyce Chai


Abstract
Large-scale, pre-trained language models (LMs) have achieved human-level performance on a breadth of language understanding tasks. However, evaluations only based on end task performance shed little light on machines’ true ability in language understanding and reasoning. In this paper, we highlight the importance of evaluating the underlying reasoning process in addition to end performance. Toward this goal, we introduce Tiered Reasoning for Intuitive Physics (TRIP), a novel commonsense reasoning dataset with dense annotations that enable multi-tiered evaluation of machines’ reasoning process. Our empirical results show that while large LMs can achieve high end performance, they struggle to support their predictions with valid supporting evidence. The TRIP dataset and our baseline results will motivate verifiable evaluation of commonsense reasoning and facilitate future research toward developing better language understanding and reasoning models.
Anthology ID:
2021.findings-emnlp.422
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
EMNLP | Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4902–4918
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.422
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.422.pdf
Code
 sled-group/verifiable-coherent-nlu
Data
TRIP