Граф трансформер
method
ID: graphtransformer
Related Papers
AMR-To-Text Generation with Graph Transformer
AbstractAbstract meaning representation (AMR)-to-text generation is the challenging task of generating natural language texts from AMR graphs, where nodes represent concepts and edges denote relations. The current state-of-the-art methods use …...
Online Back-Parsing for AMR-to-Text Generation
AbstractAMR-to-text generation aims to recover a text containing the same meaning as an input AMR graph. Current research develops increasingly powerful graph encoders to better represent AMR graphs, with decoders …...