作者位次 #2/5ACL 2026Poster· Natural Language Processing
Beyond Atomic Characters: Glyph-Aware Sub-character Alignment for Low-Resource Multilingual OCR
Mengxiao Zhu · Haixu Chen · Jiu Sha · Jie Liu · Ge Shi
摘要
Low-resource multilingual OCR faces a dual challenge: complex script structures and severe data scarcity. In such settings, existing OCR models often struggle, as coarse visual representations combined with weak linguistic priors lead to frequent errors among visually similar characters.To addres...