Update README.md

README.md

@@ -11,24 +11,26 @@ tags:
 
 
 widget:
-- text: "Η Ελλάδα είναι η ομορφότερη χώρα του κόσμου."
+- text: "Ξεχωρίζει η καθηλωτική ερμηνεία του πρωταγωνιστή."
 
 pipeline_tag: text-classification
 
 license: apache-2.0
 ---
 
-# Binary classifier to distinguish between fact (1) or opinion (0) trained on Greek and English annotated dataset.
+# Binary classifier to distinguish between fact (1) or opinion (0) trained on a mixed Greek and English annotated dataset.
 ### By the Hellenic Army Academy (SSE) and the Technical University of Crete (TUC)
 
 
 This is an XLM-Roberta-base model with a binary classification head. Given a sentence it can classify it either as a fact or an opinion, based on its content. 
+
 HuggingFace API labels:
 * Label 0: Opinion
 * Label 1: Fact
 
+The original dataset (available here: https://github.com/1024er/cbert_aug/tree/crayon/datasets/subj) containing aprox. 9000 annotated sentences (classified as subjective or objective) was translated to Greek using Google Translate. The Greek version was concatenated with the original English one to create the mixed EN-EL dataset.
 
-## Evaluation Results
+## Evaluation Results on test set
 
 | accuracy | precision | recall | f1 |
 | ----------- | ----------- | ----------- | ----------- |