Making meta-learning solve cross-prompt automatic essay scoring

Jiong Wang, Qing Zhang, Jie Liu, Xiaoyi Wang, Mingying Xu, Liguang Yang, Jianshe Zhou

Abstract: Highlights•Cross-prompt AES task focuses on training a model with a prompt generalization ability.•To achieve distribution-conscious generalization, a novel meta-learning method is proposed.•The proposed method can guide model to generalize towards target prompt distribution.•Experiments on the ASAP datasets demonstrate the proposed method’s effectiveness.