# Ancient Greek processing

SyllaBERTa is an experimental Transformer-based masked language model specifically designed for processing Ancient Greek texts, employing syllable-level tokenization.

The first and only available subword BERT model for Ancient Greek, achieving state-of-the-art fine-tuned performance in part-of-speech tagging and morphological analysis tasks.

A Transformer model for low-resource Ancient Greek, initialized with pre-training on Greek BERT and further trained on Ancient Greek corpora