Investigating Pretrained Language Models for Graph-to-Text Generation

16 Jul 2020Leonardo F. R. RibeiroMartin SchmittHinrich SchützeIryna Gurevych

Graph-to-text generation, a subtask of data-to-text generation, aims to generate fluent texts from graph-based data. Many graph-to-text models have shown strong performance in this task employing specialized graph encoders... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Data-to-Text Generation AGENDA BART-TSS BLEU 25.66 # 3
Data-to-Text Generation AGENDA BART BLEU 23.65 # 2
Data-to-Text Generation LDC2017T10 T5-TSS BLEU 48.85 # 1
AMR-to-Text Generation LDC2017T10 BART BLEU 43.72 # 1
METEOR 41.27 # 1
ChrF++ 71.27 # 1
Data-to-Text Generation LDC2017T10 BART BLEU 43.72 # 2
Data-to-Text Generation WebNLG Full BART BLEU 49.81 # 9
Data-to-Text Generation WebNLG Full T5 BLEU 59.29 # 1

Methods used in the Paper