Online Back-Parsing for AMR-to-Text Generation [article]

Xuefeng Bai, Linfeng Song, Yue Zhang
2020 arXiv   pre-print
AMR-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 based on standard language modeling being used to generate outputs. We propose a decoder that back predicts projected AMR graphs on the target sentence during text generation. As the result, our outputs can better preserve the input meaning than standard decoders. Experiments on two AMR
more » ... arks show the superiority of our model over the previous state-of-the-art system based on graph Transformer.
arXiv:2010.04520v1 fatcat:3gjb7rndizcgpj5vzutj4nisca