Logo image
A Smashed Glass Cannot Be Full: Generation of Commonsense Explanations through Prompt-based Few-shot Learning
Conference proceeding   Open access   Peer reviewed

A Smashed Glass Cannot Be Full: Generation of Commonsense Explanations through Prompt-based Few-shot Learning

Andrea Zaninello and B Magnini
Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE@ACL) , pp.18-29
1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE) (Toronto, 13/06/2023–13/06/2023)
2023
Handle:
https://hdl.handle.net/10863/50649

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.
pdf
2023.nlrse-1.3DownloadView
Open Access
url
https://dx.doi.org/10.18653/v1/2023.nlrse-1.3View

Details

Metrics

1 Record Views
Logo image