Update README.md

README.md

@@ -12,7 +12,11 @@ tags:
 
 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
-<!--- Describe your model here -->
+WikiMedical_sent_biobert_multi is a multilingual variation of [nuvocare/WikiMedical_sent_biobert](https://huggingface.co/nuvocare/WikiMedical_sent_biobert) sentence-transformers.
+It has been trained on the [nuvocare/Ted2020_en_es_fr_de_it_ca_pl_ru_nl](https://huggingface.co/datasets/nuvocare/Ted2020_en_es_fr_de_it_ca_pl_ru_nl) dataset.
+
+It uses the [nuvocare/WikiMedical_sent_biobert](https://huggingface.co/nuvocare/WikiMedical_sent_biobert) as a teacher model and a 'xlm-roberta-base' as a student model.
+The student model is trained according to the [sentence transformers documentation](https://github.com/UKPLab/sentence-transformers/blob/master/examples/training/multilingual/make_multilingual.py) to replicate embeddings across different languages. 
 
 ## Usage (Sentence-Transformers)
 
@@ -75,7 +79,19 @@ print(sentence_embeddings)
 
 ## Evaluation Results
 
-<!--- Describe how your model was evaluated -->
+The model is evaluated across languages based on 2 evaluators : [MSE](https://github.com/UKPLab/sentence-transformers/blob/master/sentence_transformers/evaluation/MSEEvaluator.py) and [translation](https://github.com/UKPLab/sentence-transformers/blob/master/sentence_transformers/evaluation/TranslationEvaluator.py). 
+
+The following table summarized the results: 
+
+| Language | MSE (x100) | Translation (source to target)| Translation (target to source)|
+|---------|---------|---------|---------|
+|    de    |    10.39    |    0.70    |    0.69    |
+|    es    |    9.9    |    0.75    |    0.74    |
+|    fr    |    10.00    |    0.72    |    0.73    |
+|    it    |    10.29    |    0.69    |    0.69    |
+|    nl    |    10.34    |    0.70    |    0.70    |
+|    pl    |    11.39    |    0.58    |    0.58    |
+|    ru    |    11.18    |    0.59    |    0.59    |
 
 For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=WikiMedical_sent_biobert_multi)