文献类型： 会议论文

第一作者： Zhu Zixiao

作者： Zhu Zixiao ¹ ; Junlang Qian ² ; Zijian Feng ¹ ; Hanzhang Zhou ¹ ; Kezhi Mao ² ;

作者机构： 1.Institute of Catastrophe Risk Management, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore##Future Resilient Systems Programme, Singapore-ETH Centre, CREATE campus, Singapore

2.School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

会议名称： [ "Conference of The North American Chapter of The Association for Computational Linguistics: Human Language Technologies" , "Conference of the North American Chapter of the Association for Computational Linguistics"]

主办单位：

页码： 1124-1137

摘要： Few-shot text classification has seen significant advancements, particularly with entailment-based methods, which typically use either class labels or intensional definitions of class labels in hypotheses for label semantics expression. In this paper, we propose EDEntail, a method that employs extensional definition (EDef) of class labels in hypotheses, aiming to express the semantics of class labels more explicitly. To achieve the above goal, we develop an algorithm to gather and select extensional descriptive words of class labels and then order and format them into a sequence to form hypotheses. Our method has been evaluated and compared with state-of-the-art models on five classification datasets. The results demonstrate that our approach surpasses the supervised-learning methods and prompt-based methods under the few-shot setting, which underlines the potential of using an extensional definition of class labels for entailment-based few-shot text classification.

分类号： tp311