Create README.md

README.md

@@ -0,0 +1,39 @@
+---
+language: 
+- ru
+- uk
+- be
+- kk
+- az
+- hy
+- ka
+- he
+- en
+- de
+tags:
+- language classification
+- text segmentation
+datasets:
+- open_subtitles
+- tatoeba
+- oscar
+---
+
+# RoBERTa for Multilabel Language Segmentation
+## Training
+RoBERTa fine-tuned on small parts of Open Subtitles, Oscar and Tatoeba datasets (~9k samples per language).
+
+Implemented heuristic algorithm for multilingual training data creation with generation of target masks- https://github.com/n1kstep/lang-classifier
+
+| data source          | language          |
+|-----------------|----------------|
+| open_subtitles    | ka, he, en, de |
+| oscar      | be, kk, az, hu |
+| tatoeba     | ru, uk         |
+
+## Validation
+The metrics obtained from validation on the another part of dataset (~1k samples per language).
+
+| Validation Loss | Precision | Recall   | F1-Score | Accuracy |
+|-----------------|-----------|----------|----------|----------|
+| 0.029172        | 0.919623  | 0.933586 | 0.926552 | 0.991883 |