Hypernym Discovery On General
Metrics
MAP
MRR
P@5
Results
Performance results of various models on this benchmark
Model Name | MAP | MRR | P@5 | Paper Title | Repository |
|---|---|---|---|---|---|
| CRIM | 19.78 | 36.10 | 19.03 | CRIM at SemEval-2018 Task 9: A Hybrid Approach to Hypernym Discovery | - |
| MFH | 8.77 | 21.39 | 7.81 | - | - |
| Apollo | 2.68 | 6.01 | 2.69 | Apollo at SemEval-2018 Task 9: Detecting Hypernymy Relations Using Syntactic Dependencies | - |
| NLP_HZ | 9.37 | 17.29 | 9.19 | NLP_HZ at SemEval-2018 Task 9: a Nearest Neighbor Approach | - |
| balAPInc | 1.36 | 3.18 | 1.30 | Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection | |
| vTE | 10.60 | 23.83 | 9.91 | - | - |
| SJTU BCMI | 5.77 | 10.56 | 5.96 | SJTU-NLP at SemEval-2018 Task 9: Neural Hypernym Discovery with Term Embeddings | - |
| 300-sparsans | 8.95 | 19.44 | 8.63 | 300-sparsans at SemEval-2018 Task 9: Hypernymy as interaction of sparse attributes | - |
0 of 8 row(s) selected.