Neural PCFG

Reported on 2 benchmarks across 1 task · 1 paper

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

Natural Language Processing2 results

Constituency ParsingonPTB Diagnostic ECG Database
Max F1 (WSJ)· 2019-06-24
52.6
best: 71.9 (Ensemble (Generative MBR))
Compound Probabilistic Context-Free Grammars for Grammar Induction arXiv:1906.10225
Constituency ParsingonPTB Diagnostic ECG Database
Mean F1 (WSJ)· 2019-06-24
50.8
best: 70.4 (Ensemble (Generative MBR))
Compound Probabilistic Context-Free Grammars for Grammar Induction arXiv:1906.10225