Arabic-specific fine-tunes of Nougat, trained on a synthetic Hindawi-derived dataset, report high in-distribution BLEU and structure accuracy for Arabic book page OCR.
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction
Arabic-specific fine-tunes of Nougat, trained on a synthetic Hindawi-derived dataset, report high in-distribution BLEU and structure accuracy for Arabic book page OCR.