SPRING DFS + silver

Reported on 8 benchmarks across 2 tasks

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

Natural Language Processing8 results

Semantic ParsingonThe Little Prince
Smatch· uses extra data
77.5
best: 79.8 (AMRBART large)
Semantic ParsingonLDC2020T02
Smatch· uses extra data
83
best: 85.4 (Graphene Smatch (MBSE paper) (IBM))
Semantic ParsingonNew3
Smatch· uses extra data
71.8
best: 76.9 (AMRBART large)
Semantic ParsingonBio
Smatch· uses extra data
59.5
best: 66.9 (StructBART + MBSE (IBM))
AMR ParsingonThe Little Prince
Smatch· uses extra data
77.5
best: 79.8 (AMRBART large)
AMR ParsingonLDC2020T02
Smatch· uses extra data
83
best: 85.4 (Graphene Smatch (MBSE paper) (IBM))
AMR ParsingonNew3
Smatch· uses extra data
71.8
best: 76.9 (AMRBART large)
AMR ParsingonBio
Smatch· uses extra data
59.5
best: 66.9 (StructBART + MBSE (IBM))