Integrating curriculum learning with meta-learning for general rhetoric identification

Dian Wang, Yang Li, Suge Wang, Xiaoli Li, Xin Chen, Shuqi Li, Jian Liao, Deyu Li

Abstract: Rhetoric is abundant and universal across different human languages. In this paper, we propose a novel curriculum learning integrated with meta-learning (CLML) model to address the task of general rhetorical identification. Specifically, we first leverage inter-category similarities to construct a dataset with curriculum characteristics for facilitating more natural easy-to-difficult learning process. Then we imitate human cognitive thinking that uses the query set in meta-learning to guide inductive network for inducing accurate class-level representations which are further improved by leveraging external class label knowledge into TapNet to construct a mapping function. Extensive experimental results demonstrate that our proposed model outperforms existing state-of-the-art models across four datasets consistently.