K-ADAPTER (F+L)

Reported on 4 benchmarks across 1 task · 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

Relation ExtractiononTACRED
F1· uses extra data· 2020-02-05
72.04
best: 86.6 (RAG4RE)
SOTA
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters arXiv:2002.01808
Relation ExtractiononTACRED
F1 (5% Few-Shot)· uses extra data· 2020-02-05
45.1
best: 69 (NLI_DeBERTa)
SOTA
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters arXiv:2002.01808
Relation ExtractiononTACRED
F1 (1% Few-Shot)· uses extra data· 2020-02-05
13.8
best: 63.7 (NLI_DeBERTa)
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters arXiv:2002.01808
Relation ExtractiononTACRED
F1 (10% Few-Shot)· uses extra data· 2020-02-05
56
best: 70.7 (SuRE (PEGASUS-large))
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters arXiv:2002.01808