Hypernym Discovery On General
Metrics
MAP
MRR
P@5
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | MAP | MRR | P@5 |
|---|---|---|---|
| crim-at-semeval-2018-task-9-a-hybrid-approach | 19.78 | 36.10 | 19.03 |
| Model 2 | 8.77 | 21.39 | 7.81 |
| apollo-at-semeval-2018-task-9-detecting | 2.68 | 6.01 | 2.69 |
| nlp_hz-at-semeval-2018-task-9-a-nearest | 9.37 | 17.29 | 9.19 |
| hypernyms-under-siege-linguistically | 1.36 | 3.18 | 1.30 |
| supervised-distributional-hypernym-discovery | 10.60 | 23.83 | 9.91 |
| sjtu-nlp-at-semeval-2018-task-9-neural | 5.77 | 10.56 | 5.96 |
| 300-sparsans-at-semeval-2018-task-9-hypernymy | 8.95 | 19.44 | 8.63 |