Command Palette
Search for a command to run...
Paraphrase Identification On Msrp
평가 지표
Accuracy
F1
평가 결과
이 벤치마크에서 각 모델의 성능 결과
| Paper Title | |||
|---|---|---|---|
| FEAT2, TFKLD, SVM, Fine-grained features | 80.41 | 85.96 | - |
| NMF factorization-unigrams-TFKLD | 72.75 | 81.48 | - |
| SWEM-concat | 71.5 | 81.3 | Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms |
0 of 3 row(s) selected.