Ossetic-COT: first morphologically annotated corpus and BERT-based analyzer for Iron Ossetic

The authors present Ossetic-COT, the first morphologically annotated corpus for Iron Ossetic that conforms to the Universal Dependencies schema. The dataset comprises 5454 manually annotated sentences from the Iron Ossetic Corpus of Oral Texts, containing a total of 74032 tokens.

• The corpus is built using the Universal Dependencies schema.
• It includes 5454 sentences and 74032 tokens.
• A BERT-based morphological analyzer was trained on this data.
• The analyzer achieves a tag accuracy of 95.60%.

This work provides essential resources for the linguistic analysis of Iron Ossetic, enabling accurate morphological processing through the developed analyzer.