stack-Transformer + self-learning (IBM)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Natural Language Processing4 results

Semantic ParsingonLDC2014T12
F1 Full· 2020-10-20
78.2
best: 78.5 (APT (IBM))
SOTA
Pushing the Limits of AMR Parsing with Self-Learning arXiv:2010.10673
AMR ParsingonLDC2014T12
F1 Full· 2020-10-20
78.2
best: 78.5 (APT (IBM))
SOTA
Pushing the Limits of AMR Parsing with Self-Learning arXiv:2010.10673
Semantic ParsingonLDC2017T10
Smatch· uses extra data· 2020-10-20
81.3
best: 86.7 (StructBART + MBSE (IBM))
Pushing the Limits of AMR Parsing with Self-Learning arXiv:2010.10673
AMR ParsingonLDC2017T10
Smatch· uses extra data· 2020-10-20
81.3
best: 86.7 (StructBART + MBSE (IBM))
Pushing the Limits of AMR Parsing with Self-Learning arXiv:2010.10673