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
- Original:
- 2021.findings-emnlp.422v1
- Version 2:
- 2021.findings-emnlp.422v2
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4902–4918
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.422
- DOI:
- 10.18653/v1/2021.findings-emnlp.422
- Cite (ACL):
- Shane Storks, Qiaozi Gao, Yichi Zhang, and Joyce Chai. 2021. Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4902–4918, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding (Storks et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2021.findings-emnlp.422.pdf
- Code
- sled-group/verifiable-coherent-nlu
- Data
- TRIP