PInKS: Preconditioned Commonsense Inference with Minimal Supervision

Ehsan Qasemi, Piyush Khanna, Qiang Ning, Muhao Chen


Abstract
Reasoning with preconditions such as “glass can be used for drinking water unless the glass is shattered” remains an open problem for language models. The main challenge lies in the scarcity of preconditions data and the model’s lack of support for such reasoning. We present PInKS , Preconditioned Commonsense Inference with WeaK Supervision, an improved model for reasoning with preconditions through minimum supervision. We show, empirically and theoretically, that PInKS improves the results on benchmarks focused on reasoning with the preconditions of commonsense knowledge (up to 40% Macro-F1 scores). We further investigate PInKS through PAC-Bayesian informativeness analysis, precision measures, and ablation study.
Anthology ID:
2022.aacl-main.26
Volume:
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2022
Address:
Online only
Editors:
Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
Venues:
AACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
320–336
Language:
URL:
https://aclanthology.org/2022.aacl-main.26
DOI:
Bibkey:
Cite (ACL):
Ehsan Qasemi, Piyush Khanna, Qiang Ning, and Muhao Chen. 2022. PInKS: Preconditioned Commonsense Inference with Minimal Supervision. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 320–336, Online only. Association for Computational Linguistics.
Cite (Informal):
PInKS: Preconditioned Commonsense Inference with Minimal Supervision (Qasemi et al., AACL-IJCNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.aacl-main.26.pdf
Software:
 2022.aacl-main.26.Software.zip
Dataset:
 2022.aacl-main.26.Dataset.zip