Researchers have developed Ossetic-COT, the first morphologically annotated corpus for Iron Ossetic, adhering to the Universal Dependencies schema. This corpus contains over 5400 manually annotated sentences, totaling more than 74,000 tokens. Utilizing this dataset, a BERT-based morphological analyzer was trained, achieving a notable tag accuracy of 95.60%. AI
IMPACT This work provides a foundational resource for developing more advanced NLP tools for the Iron Ossetic language.
RANK_REASON The cluster describes the creation of a new annotated corpus and a trained language model, which falls under research.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
