Analogy recognition on UNIT 4
76.15AccuracyRoBERTa-Large + ANALOGYKB
Evaluation results
| Method | Links | |
|---|---|---|
| RoBERTa-Large + ANALOGYKBBackbone=RoBERTa-Large, Knowledge Enhancement=ANALOGYKB, Filtering=Checked2023.05 | 76.15 | |
| DeBERTa-v3 + ANALOGYKBBackbone=DeBERTa-v3, Knowledge Enhancement=ANALOGYKB, Filtering=Checked2023.05 | 75.3 | |
| Human2023.05 | 66.66 | |
| Word Embedding from InstructGPTBackbone=InstructGPT, Embedding Type=Word2023.05 | 62.6 | |
| Word Embedding from RoBERTa-LargeBackbone=RoBERTa-Large, Embedding Type=Word2023.05 | 57.4 | |
| Sentence Embedding from SimCSEBackbone=SimCSE, Embedding Type=Sentence2023.05 | 50.32 | |
| DeBERTa-v3Backbone=DeBERTa-v32023.05 | 46.99 | |
| Sentence Embedding from SentenceBERTBackbone=SentenceBERT, Embedding Type=Sentence2023.05 | 46 | |
| DeBERTa-v3 + ANALOGYKB (w/o check)Backbone=DeBERTa-v3, Knowledge Enhancement=ANALOGYKB, Filtering=Unchecked2023.05 | 45.6 | |
| RoBERTa-LargeBackbone=RoBERTa-Large2023.05 | 40.04 | |
| RoBERTa-Large + ANALOGYKB (w/o check)Backbone=RoBERTa-Large, Knowledge Enhancement=ANALOGYKB, Filtering=Unchecked2023.05 | 39.25 | |
| LUKEBackbone=LUKE2023.05 | 39.12 | |
| ERNIEBackbone=ERNIE2023.05 | 36.8 | |
| BERT-LargeBackbone=BERT-Large2023.05 | 34.49 | |
| T5-LargeBackbone=T5-Large2023.05 | 31.25 |