Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models

Tassilo Klein, Moin Nabi


Abstract
Can we get existing language models and refine them for zero-shot commonsense reasoning? This paper presents an initial study exploring the feasibility of zero-shot commonsense reasoning for the Winograd Schema Challenge by formulating the task as self-supervised refinement of a pre-trained language model. In contrast to previous studies that rely on fine-tuning annotated datasets, we seek to boost conceptualization via loss landscape refinement. To this end, we propose a novel self-supervised learning approach that refines the language model utilizing a set of linguistic perturbations of similar concept relationships. Empirical analysis of our conceptually simple framework demonstrates the viability of zero-shot commonsense reasoning on multiple benchmarks.
Anthology ID:
2021.emnlp-main.688
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8737–8743
Language:
URL:
https://aclanthology.org/2021.emnlp-main.688
DOI:
10.18653/v1/2021.emnlp-main.688
Bibkey:
Cite (ACL):
Tassilo Klein and Moin Nabi. 2021. Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8737–8743, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models (Klein & Nabi, EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2021.emnlp-main.688.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/2021.emnlp-main.688.mp4
Code
 sap-samples/emnlp2021-contrastive-refinement
Data
GAP Coreference DatasetWSCWinoBiasWinoGrande