Add evaluation results to README.md
#2
by
atasoglu
- opened
README.md
CHANGED
@@ -90,9 +90,15 @@ print(sentence_embeddings)
|
|
90 |
|
91 |
## Evaluation Results
|
92 |
|
93 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
94 |
|
95 |
-
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=atasoglu/roberta-small-turkish-clean-uncased-nli-stsb-tr)
|
96 |
|
97 |
|
98 |
## Training
|
|
|
90 |
|
91 |
## Evaluation Results
|
92 |
|
93 |
+
Achieved results on the [STS-b](https://huggingface.co/datasets/emrecan/stsb-mt-turkish) test split are given below:
|
94 |
+
|
95 |
+
```txt
|
96 |
+
Cosine-Similarity : Pearson: 0.8027 Spearman: 0.8012
|
97 |
+
Manhattan-Distance: Pearson: 0.7922 Spearman: 0.7892
|
98 |
+
Euclidean-Distance: Pearson: 0.7919 Spearman: 0.7890
|
99 |
+
Dot-Product-Similarity: Pearson: 0.7547 Spearman: 0.7445
|
100 |
+
```
|
101 |
|
|
|
102 |
|
103 |
|
104 |
## Training
|