Graph Pre-training for AMR Parsing and Generation
This addresses the need for better modeling of semantic graphs in natural language processing, representing an incremental improvement by adapting existing pre-training methods to graph structures.
The paper tackles the problem of suboptimal structural knowledge in pre-trained language models for AMR parsing and generation by introducing graph self-supervised training to improve structure awareness, resulting in superior performance in experiments on both tasks.
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, respectively. 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. Experiments on both AMR parsing and AMR-to-text generation show the superiority of our model. To our knowledge, we are the first to consider pre-training on semantic graphs.