ML Research Wiki / Benchmarks / Irish Text Diacritization / Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems

Multilingual Dataset for Training and Evaluating Diacritics Restoration Systems

Irish Text Diacritization Benchmark

Performance Over Time

📊 Showing 1 results | 📏 Metric: Alpha-Word accuracy

Top Performing Models

Rank Model Paper Alpha-Word accuracy Date Code
1 BERT Diacritics Restoration using BERT with Analysis on Czech language 98.88 2021-05-24 📦 ufal/bert-diacritics-restoration

All Papers (1)

ufal/bert-diacritics-restoration