DIORA

Reported on 4 benchmarks across 1 task

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

Natural Language Processing4 results

Constituency ParsingonPTB Diagnostic ECG Database
Max F1 (WSJ)
49.6
best: 71.9 (Ensemble (Generative MBR))
Constituency ParsingonPTB Diagnostic ECG Database
Max F1 (WSJ10)
68.5
best: 71.8 (S-DIORA)
Constituency ParsingonPTB Diagnostic ECG Database
Mean F1 (WSJ)
48.9
best: 70.4 (Ensemble (Generative MBR))
Constituency ParsingonPTB Diagnostic ECG Database
Mean F1 (WSJ10)
67.7
best: 74.2 (inside-outside co-training + weak supervision)