Предварительное обучение с маскированием графа
method
ID: graphmaskingpretraining
Related Papers
Self-supervised Graph Masking Pre-training for Graph-to-Text Generation
AbstractLarge-scale pre-trained language models (PLMs) have advanced Graph-to-Text (G2T) generation by processing the linearised version of a graph. However, the linearisation is known to ignore the structural information. Additionally, PLMs …...