Added information on the cross-lingual capabilities of the model

README.md

@@ -275,6 +275,30 @@ The classifier was compared with other classifiers on 2 additional genre dataset
 At cross-dataset and cross-lingual experiments, it was shown that the X-GENRE classifier,
 trained on all three datasets, outperforms classifiers that were trained on just one of the datasets.
 
+Additionally, we evaluated the X-GENRE classifier on a multilingual X-GINCO dataset that comprises samples
+of texts from the MaCoCu web corpora (http://hdl.handle.net/11356/1969).
+The X-GINCO dataset comprises 790 instances in 10 languages - 
+Albanian, Croatian, Catalan, Greek, Icelandic, Macedonian, Maltese, Slovenian, Turkish, and Ukrainian.
+To evaluate the performance on genre labels, the dataset is balanced by labels,
+and the vague label "Other" is not included.
+Additionally, instances that were predicted with a confidence score below 0.80 were not included in the test dataset.
+The evaluation shows high cross-lingual performance of the model,
+even when applied to languages that are not related to the training languages (English and Slovenian) and when applied on non-Latin scripts.
+The outlier is Maltese, on which classifier does not perform well - 
+we presume that this is due to the fact that Maltese is not included in the pretraining data of the XLM-RoBERTa model.
+
+| Genre label   | ca   | el   | hr   | is   | mk   | sl   | sq   | tr   | uk   | Avg  | mt   |
+|---------------|------|------|------|------|------|------|------|------|------|------|------|
+| News          | 0.82 | 0.90 | 0.95 | 0.73 | 0.91 | 0.90 | 0.89 | 0.95 | 1.00 | 0.89 | 0.69 |
+| Opinion/Argumentation       | 0.84 | 0.87 | 0.78 | 0.82 | 0.78 | 0.82 | 0.67 | 0.82 | 0.91 | 0.81 | 0.33 |
+| Instruction   | 0.75 | 0.71 | 0.75 | 0.78 | 1.00 | 1.00 | 0.95 | 0.90 | 0.95 | 0.86 | 0.69 |
+| Information/Explanation   | 0.72 | 0.70 | 0.95 | 0.50 | 0.84 | 0.90 | 0.80 | 0.82 | 1.00 | 0.80 | 0.52 |
+| Promotion     | 0.78 | 0.62 | 0.87 | 0.75 | 0.95 | 1.00 | 0.95 | 0.86 | 0.78 | 0.84 | 0.82 |
+| Forum         | 0.84 | 0.95 | 0.91 | 0.95 | 1.00 | 1.00 | 0.78 | 0.89 | 0.95 | 0.91 | 0.18 |
+| Prose/Lyrical | 0.91 | 1.00 | 0.86 | 1.00 | 0.95 | 0.91 | 0.86 | 0.95 | 1.00 | 0.93 | 0.18 |
+| Legal         | 0.95 | 1.00 | 1.00 | 0.84 | 0.95 | 0.95 | 0.95 | 1.00 | 1.00 | 0.96 | /    |
+| Macro-F1      | 0.83 | 0.84 | 0.88 | 0.80 | 0.92 | 0.94 | 0.85 | 0.90 | 0.95 | 0.87 | 0.49 |
+
 ### Fine-tuning hyperparameters
 
 Fine-tuning was performed with `simpletransformers`.