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
- 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)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2023.nlrse-1.3.pdf