K-Adapter ( fac-adapter )

Reported on 3 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 Processing3 results

Entity Typingon Open Entity
F1· 2020-02-05
77.6916
SOTA
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters arXiv:2002.01808
Entity Typingon Open Entity
Precision· 2020-02-05
79.6712
SOTA
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters arXiv:2002.01808
Entity Typingon Open Entity
Recall· 2020-02-05
75.8081
best: 76.2774 (K-Adapter ( fac-adapter + lin-adapter ))
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters arXiv:2002.01808