AI summaryⓘ
The authors created the first set of Iron Ossetic language texts that are labeled with detailed grammar information following a standard framework called Universal Dependencies. They worked on 5,454 sentences containing over 74,000 words. Using this labeled data, they trained a computer model based on BERT to recognize grammatical categories in Iron Ossetic. Their model correctly identified grammar tags about 96% of the time.
Iron OsseticUniversal Dependenciesmorphological annotationcorpusBERTmorphological analyzertag accuracynatural language processinggrammatical taggingmachine learning
Abstract
In this work we present the first morphologically annotated corpus for Iron Ossetic that conforms to the Universal Dependencies schema. The corpus includes 5454 manually annotated sentences from the Iron Ossetic Corpus of Oral Texts, containing 74032 tokens. We use this corpus to train a BERT-based morphological analyzer. The analyzer achieves tag accuracy of 95.60%.