Hierarchical Curriculum Learning for AMR Parsing
share
Abstract Meaning Representation (AMR) parsing translates sentences to the semantic representation with a hierarchical structure, which is recently empowered by pretrained encoder-decoder models. However, the flat sentence-to-AMR training paradigm impedes the representation learning of concepts and relations in the deeper AMR sub-graph. To make the sequence-to-sequence models better adapt to the inherent AMR structure, we propose a hierarchical curriculum learning (HCL) which consists of (1) structure-level curriculum (SC) and (2) instance-level curriculum (IC). SC switches progressively from shallow to deep AMR sub-graphs while IC transits from easy to hard AMR instances during training. Extensive experiments show that BART trained with HCL achieves the state-of-the-art performance on the AMR-2.0 and AMR-3.0 benchmark, and significantly outperforms baselines on the structure-dependent evaluation metrics and hard instances.
READ FULL TEXT
