HBSG

Reported on 8 benchmarks across 4 tasks

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

Natural Language Processing6 results

Data-to-Text GenerationonVIST
BLEU-4
15.4
best: 16.7 (HEGR)
Data-to-Text GenerationonVIST
METEOR
36.5
best: 37.8 (HEGR)
Visual StorytellingonVIST
BLEU-4
15.4
best: 16.7 (HEGR)
Visual StorytellingonVIST
METEOR
36.5
best: 37.8 (HEGR)
Story GenerationonVIST
BLEU-4
15.4
best: 16.7 (HEGR)
Story GenerationonVIST
METEOR
36.5
best: 37.8 (HEGR)

Adversarial2 results

Text GenerationonVIST
BLEU-4
15.4
best: 16.7 (HEGR)
Text GenerationonVIST
METEOR
36.5
best: 37.8 (HEGR)