%0 Conference Proceedings %T TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification %A Wang, Chengyu %A Wang, Jianing %A Qiu, Minghui %A Huang, Jun %A Gao, Ming %Y Moens, Marie-Francine %Y Huang, Xuanjing %Y Specia, Lucia %Y Yih, Scott Wen-tau %S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing %D 2021 %8 November %I Association for Computational Linguistics %C Online and Punta Cana, Dominican Republic %F wang-etal-2021-transprompt %X Recent studies have shown that prompts improve the performance of large pre-trained language models for few-shot text classification. Yet, it is unclear how the prompting knowledge can be transferred across similar NLP tasks for the purpose of mutual reinforcement. Based on continuous prompt embeddings, we propose TransPrompt, a transferable prompting framework for few-shot learning across similar tasks. In TransPrompt, we employ a multi-task meta-knowledge acquisition procedure to train a meta-learner that captures cross-task transferable knowledge. Two de-biasing techniques are further designed to make it more task-agnostic and unbiased towards any tasks. After that, the meta-learner can be adapted to target tasks with high accuracy. Extensive experiments show that TransPrompt outperforms single-task and cross-task strong baselines over multiple NLP tasks and datasets. We further show that the meta-learner can effectively improve the performance on previously unseen tasks; and TransPrompt also outperforms strong fine-tuning baselines when learning with full training sets. %R 10.18653/v1/2021.emnlp-main.221 %U https://aclanthology.org/2021.emnlp-main.221 %U https://doi.org/10.18653/v1/2021.emnlp-main.221 %P 2792-2802