A Graph-to-Sequence Model for AMR-to-Text Generation

ACL 2018 Linfeng SongYue ZhangZhiguo WangDaniel Gildea

The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph. The current state-of-the-art method uses a sequence-to-sequence model, leveraging LSTM for encoding a linearized AMR structure... (read more)

PDF Abstract

Evaluation Results from the Paper


 SOTA for Graph-to-Sequence on LDC2015E86: (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
COMPARE
Graph-to-Sequence LDC2015E86: GRN BLEU 33.6 # 1
Text Generation LDC2016E25 Graph2Seq BLEU 22 # 1