Update README.md

README.md

@@ -158,6 +158,8 @@ Note: For French and Italian, the training data remains in German, while the tes
 
 ### Results
 
+Making use of an unsupervised training approach, Swissbert for Sentence Embeddings achieves comparable results as the best-performing multilingual Sentence-BERT model in the semantic textual similarity task for German and outperforms it in the French text classification task.
+
 | Evaluation task        |swissbert |         |swissbert for SE|         |Sentence-BERT|         |
 |------------------------|----------|---------|----------------|---------|-------------|---------|
 |                        |accuracy  |f1-score |accuracy        |f1-score |accuracy     |f1-score |