Graph Pre-training for AMR Parsing and Generation

Anonymous

Abstract: Abstract meaning representation (AMR) highlights the core semantic information of text in a graph structure.Recently, pre-trained language models (PLMs) have advanced tasks of AMR parsing and AMR-to-text generation.However, PLMs are typically pre-trained on textual data, thus are sub-optimal for modeling structural knowledge.To this end, we investigate graph self-supervised training to improve the structure awareness of PLMs over AMR graphs.In particular, we introduce two graph auto-encoding strategies for graph-to-graph pre-training and four tasks to integrate text and graph information during pre-training.We further design a unified framework to bridge the gap between pre-training and fine-tuning tasks.Experimental results on both AMR parsing and AMR-to-text generation tasks show the superiority of our model.To our knowledge, we are the first to consider pre-training on AMR graphs.