BART-large

Reported on 6 benchmarks across 5 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Data-to-Text GenerationonAGENDA
BLEU· 2020-07-16
23.65
best: 25.66 (BART-large+ STA)
Investigating Pretrained Language Models for Graph-to-Text Generation arXiv:2007.08426
KG-to-Text GenerationonAGENDA
BLEU· 2020-07-16
23.65
best: 25.66 (BART-large+ STA)
Investigating Pretrained Language Models for Graph-to-Text Generation arXiv:2007.08426
Response GenerationonSIMMC2.0
BLEU
33.1
best: 34.1 (PaCE)

Speech2 results

DialogueonSIMMC2.0
Act F1
96.3
best: 97.1 (PaCE)
DialogueonSIMMC2.0
Slot F1
88.3

Adversarial1 result

Text GenerationonAGENDA
BLEU· 2020-07-16
23.65
best: 25.66 (BART-large+ STA)
Investigating Pretrained Language Models for Graph-to-Text Generation arXiv:2007.08426