MLMET

Reported on 4 benchmarks across 1 task · 2 papers · 4 SOTA

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

Natural Language Processing5 results

Entity TypingonOntonotes v5 (English)
F1· uses extra data· 2021-06-08
49.1
SOTA
Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model arXiv:2106.04098
Entity TypingonOntonotes v5 (English)
Precision· uses extra data· 2021-06-08
53.6
SOTA
Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model arXiv:2106.04098
Entity TypingonOntonotes v5 (English)
Recall· uses extra data· 2021-06-08
45.3
SOTA
Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model arXiv:2106.04098
Entity TypingonOpen Entity
F1· 2020-10-02
78.2
SOTA
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention arXiv:2010.01057
Entity TypingonOpen Entity
F1· 2021-06-08
49.1
best: 78.2
Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model arXiv:2106.04098