Analogy recognition on BATS
92.42AccuracyDeBERTa-v3 + ANALOGYKB
Evaluation results
| Method | Links | |
|---|---|---|
| DeBERTa-v3 + ANALOGYKBBackbone=DeBERTa-v3, Knowledge Enhancement=ANALOGYKB, Filtering=Checked2023.05 | 92.42 | |
| RoBERTa-Large + ANALOGYKBBackbone=RoBERTa-Large, Knowledge Enhancement=ANALOGYKB, Filtering=Checked2023.05 | 90.93 | |
| Human2023.05 | 84.85 | |
| LUKEBackbone=LUKE2023.05 | 82.82 | |
| ERNIEBackbone=ERNIE2023.05 | 82.54 | |
| RoBERTa-Large + ANALOGYKB (w/o check)Backbone=RoBERTa-Large, Knowledge Enhancement=ANALOGYKB, Filtering=Unchecked2023.05 | 80.3 | |
| DeBERTa-v3Backbone=DeBERTa-v32023.05 | 79.54 | |
| DeBERTa-v3 + ANALOGYKB (w/o check)Backbone=DeBERTa-v3, Knowledge Enhancement=ANALOGYKB, Filtering=Unchecked2023.05 | 78.82 | |
| Word Embedding from InstructGPTBackbone=InstructGPT, Embedding Type=Word2023.05 | 78.3 | |
| RoBERTa-LargeBackbone=RoBERTa-Large2023.05 | 78.2 | |
| T5-LargeBackbone=T5-Large2023.05 | 77.37 | |
| Word Embedding from RoBERTa-LargeBackbone=RoBERTa-Large, Embedding Type=Word2023.05 | 72 | |
| BERT-LargeBackbone=BERT-Large2023.05 | 70.1 | |
| Sentence Embedding from SentenceBERTBackbone=SentenceBERT, Embedding Type=Sentence2023.05 | 68 | |
| Sentence Embedding from SimCSEBackbone=SimCSE, Embedding Type=Sentence2023.05 | 66.54 |