LISA

Reported on 3 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 Processing5 results

Semantic Role LabelingonCoNLL 2012
F1· 2018-04-23
97.2
SOTA
Linguistically-Informed Self-Attention for Semantic Role Labeling arXiv:1804.08199
Semantic Role LabelingonCoNLL 2005
F1· 2018-04-23
98.4
SOTA
Linguistically-Informed Self-Attention for Semantic Role Labeling arXiv:1804.08199
Semantic Role LabelingonCoNLL 2005
F1· 2018-04-23
86.04
best: 98.4
Linguistically-Informed Self-Attention for Semantic Role Labeling arXiv:1804.08199
Semantic Role LabelingonCoNLL 2005
F1· 2018-04-23
84.99
best: 98.4
Linguistically-Informed Self-Attention for Semantic Role Labeling arXiv:1804.08199
Semantic Role LabelingonCoNLL 2012
F1· 2018-04-23
82.33
best: 97.2
Linguistically-Informed Self-Attention for Semantic Role Labeling arXiv:1804.08199

Computer Vision1 result

Visual LocalizationonOxford Radar RobotCar (Full-6)
Mean Translation Error
2.74
best: 2.67 (LightLoc)