Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, and is recently empowered by pretrained sequence-to-sequence models. However, there exists a gap between their flat training objective (i.e., equally treats all output tokens) and the hierarchical AMR structure, which limits the model generalization. To bridge this gap, we propose a Hierarchical Curriculum Learning (HCL) framework with Structure-level (SC) and Instance-level Curricula (IC). SC switches progressively from core to detail AMR semantic elements while IC transits from structure-simple to -complex AMR instances during training. Through these two warming-up processes, HCL reduces the difficulty of learning complex structures, thus the flat model can better adapt to the AMR hierarchy. Extensive experiments on AMR2.0, AMR3.0, structure-complex and out-of-distribution situations verify the effectiveness of HCL.
@article{arxiv.2110.07855,
title = {Hierarchical Curriculum Learning for AMR Parsing},
author = {Peiyi Wang and Liang Chen and Tianyu Liu and Damai Dai and Yunbo Cao and Baobao Chang and Zhifang Sui},
journal= {arXiv preprint arXiv:2110.07855},
year = {2022}
}
Comments
ACL2022 short paper; Code and model are available a https://github.com/Wangpeiyi9979/HCL-Text2AMR