Semantic Textual Similarity On Senteval
평가 지표
MRPC
SICK-E
SICK-R
STS
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | MRPC | SICK-E | SICK-R | STS |
|---|---|---|---|---|
| training-complex-models-with-multi-task-weak | 91.5/88.5 | - | - | 90.1/89.7* |
| xlnet-generalized-autoregressive-pretraining | 93.0/90.7 | - | - | 91.6/91.1* |
| learning-general-purpose-distributed-sentence | 78.6/84.4 | 87.8 | 0.888 | 78.9/78.6 |
| discriminative-improvements-to-distributional | 80.4/85.9 | - | - | - |
| improving-multi-task-deep-neural-networks-via | 92.7/90.3 | - | - | 91.1/90.7* |
| supervised-learning-of-universal-sentence | 76.2/83.1 | 86.3 | 0.884 | 75.8/75.5 |