TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answering
This addresses the challenge of mining effective commonsense knowledge without labeled data for researchers in NLP, though it is incremental as it builds on existing prompt-based methods.
The paper tackles the problem of poor generalization in unsupervised commonsense question answering by proposing a two-stage prompt-based framework that leverages implicit knowledge in pre-trained language models, resulting in significant improvements on tasks like CommonsenseQA, OpenBookQA, and SocialIQA.
Unsupervised commonsense question answering requires mining effective commonsense knowledge without the rely on the labeled task data. Previous methods typically retrieved from traditional knowledge bases or used pre-trained language models (PrLMs) to generate fixed types of knowledge, which have poor generalization ability. In this paper, we aim to address the above limitation by leveraging the implicit knowledge stored in PrLMs and propose a two-stage prompt-based unsupervised commonsense question answering framework (TSGP). Specifically, we first use knowledge generation prompts to generate the knowledge required for questions with unlimited types and possible candidate answers independent of specified choices. Then, we further utilize answer generation prompts to generate possible candidate answers independent of specified choices. Experimental results and analysis on three different commonsense reasoning tasks, CommonsenseQA, OpenBookQA, and SocialIQA, demonstrate that TSGP significantly improves the reasoning ability of language models in unsupervised settings. Our code is available at: https://github.com/Yueqing-Sun/TSGP.