GPT-too: A language-model-first approach for AMR-to-text generation

ACL 2020 Manuel MagerRamon Fernandez AstudilloTahira NaseemMd Arafat SultanYoung-Suk LeeRadu FlorianSalim Roukos

Meaning Representations (AMRs) are broad-coverage sentence-level semantic graphs. Existing approaches to generating text from AMR have focused on training sequence-to-sequence or graph-to-sequence models on AMR annotated data only... (read more)

PDF Abstract ACL 2020 PDF ACL 2020 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
AMR-to-Text Generation LDC2017T10 GPT-too AMR-to-Text BLEU 33.02 # 2
METEOR 37.68 # 2
ChrF++ 63.89 # 2

Methods used in the Paper