ML Research Wiki / Benchmarks / Entity Typing / Open Entity

Open Entity

Entity Typing Benchmark

Performance Over Time

📊 Showing 13 results | 📏 Metric: F1

Top Performing Models

Rank Model Paper F1 Date Code
1 MLMET LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention 78.20 2020-10-02 📦 huggingface/transformers 📦 PaddlePaddle/PaddleNLP 📦 studio-ousia/luke
2 MCCE-B (replicated by Adaseq) Recall, Expand and Multi-Candidate Cross-Encode: Fast and Accurate Ultra-Fine Entity Typing 52.10 2022-12-18 📦 modelscope/adaseq
3 Prompt + NPCRF (replicated by Adaseq) Modeling Label Correlations for Ultra-Fine Entity Typing with Neural Pairwise Conditional Random Field 50.10 2022-12-03 📦 modelscope/adaseq
4 UniST-Large Unified Semantic Typing with Meaningful Label Inference 49.90 2022-05-04 📦 luka-group/unist
5 Prompt Learning (replicated by Adaseq)) Modeling Label Correlations for Ultra-Fine Entity Typing with Neural Pairwise Conditional Random Field 49.30 2022-12-03 📦 modelscope/adaseq
6 MLMET Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model 49.10 2021-06-08 📦 HKUST-KnowComp/MLMET
7 RoBERTa-Large + NPCRF (replicated by Adaseq) Modeling Label Correlations for Ultra-Fine Entity Typing with Neural Pairwise Conditional Random Field 47.30 2022-12-03 📦 modelscope/adaseq
8 LRN Fine-grained Entity Typing via Label Reasoning 45.40 2021-09-13 -
9 Box4Type Modeling Fine-Grained Entity Types with Box Embeddings 44.80 2021-01-02 📦 yasumasaonoe/Box4Types
10 RoBERTa-Large (replicated by Adaseq) Modeling Label Correlations for Ultra-Fine Entity Typing with Neural Pairwise Conditional Random Field 43.80 2022-12-03 📦 modelscope/adaseq

All Papers (13)