Joint cross-script training on Arabic-script datasets reduces CER in low-resource regimes, with improvements concentrated on shared characters and new SOTA results on Persian.
Salaheldin Kasem, M
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
Sequence-level modeling, not shared visual features, explains cross-language transfer improvements in low-resource Arabic-script HTR.
citing papers explorer
-
Cross-Language Learning within Arabic Script for Low-Resource HTR
Joint cross-script training on Arabic-script datasets reduces CER in low-resource regimes, with improvements concentrated on shared characters and new SOTA results on Persian.
-
Understanding Cross-Language Transfer Improvements in Low-Resource HTR: The Role of Sequence Modeling
Sequence-level modeling, not shared visual features, explains cross-language transfer improvements in low-resource Arabic-script HTR.