Analogy recognition on UNIT 2
88.32AccuracyDeBERTa-v3 + ANALOGYKB
Evaluation results
| Method | Links | |
|---|---|---|
| DeBERTa-v3 + ANALOGYKBBackbone=DeBERTa-v3, Knowledge Enhancement=ANALOGYKB, Filtering=Checked2023.05 | 88.32 | |
| Human2023.05 | 87.5 | |
| RoBERTa-Large + ANALOGYKBBackbone=RoBERTa-Large, Knowledge Enhancement=ANALOGYKB, Filtering=Checked2023.05 | 87.28 | |
| Word Embedding from InstructGPTBackbone=InstructGPT, Embedding Type=Word2023.05 | 65.39 | |
| Word Embedding from RoBERTa-LargeBackbone=RoBERTa-Large, Embedding Type=Word2023.05 | 58.3 | |
| Sentence Embedding from SimCSEBackbone=SimCSE, Embedding Type=Sentence2023.05 | 54.29 | |
| Sentence Embedding from SentenceBERTBackbone=SentenceBERT, Embedding Type=Sentence2023.05 | 53.4 | |
| DeBERTa-v3Backbone=DeBERTa-v32023.05 | 50 | |
| RoBERTa-LargeBackbone=RoBERTa-Large2023.05 | 46.05 | |
| DeBERTa-v3 + ANALOGYKB (w/o check)Backbone=DeBERTa-v3, Knowledge Enhancement=ANALOGYKB, Filtering=Unchecked2023.05 | 45.18 | |
| RoBERTa-Large + ANALOGYKB (w/o check)Backbone=RoBERTa-Large, Knowledge Enhancement=ANALOGYKB, Filtering=Unchecked2023.05 | 44.2 | |
| T5-LargeBackbone=T5-Large2023.05 | 34.65 | |
| LUKEBackbone=LUKE2023.05 | 34.64 | |
| ERNIEBackbone=ERNIE2023.05 | 34.21 | |
| BERT-LargeBackbone=BERT-Large2023.05 | 32.89 |