Online Back-Parsing for AMR-to-Text Generation

EMNLP 2020  ·  Xuefeng Bai, Linfeng Song, Yue Zhang ·

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 benchmarks show the superiority of our model over the previous state-of-the-art system based on graph Transformer.

PDF Abstract EMNLP 2020 PDF EMNLP 2020 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
AMR-to-Text Generation LDC2017T10 Online Back-Parsing BLEU 34.19 # 7