A smashed glass cannot be full: Generation of Commonsense Explanations through Prompt-based Few-shot Learning

Andrea Zaninello, Bernardo Magnini


Abstract
We assume that providing explanations is a process to elicit implicit knowledge in human communication, and propose a general methodology to generate commonsense explanations from pairs of semantically related sentences. We take advantage of both prompting applied to large, encoder-decoder pre-trained language models, and few-shot learning techniques, such as pattern-exploiting training. Experiments run on the e-SNLI dataset show that the proposed method achieves state-of-the-art results on the explanation generation task, with a substantial reduction of labelled data. The obtained results open new perspective on a number of tasks involving the elicitation of implicit knowledge.
Anthology ID:
2023.nlrse-1.3
Volume:
Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE)
Month:
June
Year:
2023
Address:
Toronto, Canada
Editors:
Bhavana Dalvi Mishra, Greg Durrett, Peter Jansen, Danilo Neves Ribeiro, Jason Wei
Venue:
NLRSE
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18–29
Language:
URL:
https://aclanthology.org/2023.nlrse-1.3
DOI:
10.18653/v1/2023.nlrse-1.3
Bibkey:
Cite (ACL):
Andrea Zaninello and Bernardo Magnini. 2023. A smashed glass cannot be full: Generation of Commonsense Explanations through Prompt-based Few-shot Learning. In Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE), pages 18–29, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
A smashed glass cannot be full: Generation of Commonsense Explanations through Prompt-based Few-shot Learning (Zaninello & Magnini, NLRSE 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.nlrse-1.3.pdf