Joint w/ Global

Reported on 5 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 Processing5 results

Relation ExtractiononACE 2005
NER Micro F1
80.8
best: 91.3 (ASP+T5-3B)
Relation ExtractiononACE 2005
RE Micro F1
52.1
best: 73 (PL-Marker)
Relation ExtractiononACE 2005
RE+ Micro F1
49.5
best: 71.1 (PL-Marker)
Relation ExtractiononACE 2004
NER Micro F1
79.7
best: 90.4 (PL-Marker)
Relation ExtractiononACE 2004
RE+ Micro F1
45.3
best: 66.5 (PL-Marker)