跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.13609 · v1

Post-OCR Correction of Mixed-Script Uzbek Text: Byte-Level ByT5 with an Empirical Homoglyph Noise Matrix

首次提交 2026-11-10 13:35
版本更新 2026-11-10 13:35
雷达观测 2026-11-11 11:04
arXiv ↗PDF ↗

摘要

In Uzbek official and technical documents, a large share of OCR errors is caused not by poor image quality but by characters that are visually identical across the two alphabets in use. Because the script transition is still under way, Cyrillic and Latin appear on the same page and often within a single sentence, and in our measurements the density of homoglyph errors on such pages is close to five times higher than in single-script text. We study this problem in a setting where the corpus of engineering-geological and ICT infrastructure reports may not leave the organisation, so every stage was executed on local hardware. The proposed system combines a byte-level ByT5 model with a noise generator whose sampling weights are estimated from 359 manually classified error events, together with a Levenshtein-bounded conservative decoding rule. On a Gold set of 5,204 line pairs it lowers the character error rate from 0.0578 to 0.0369, restores 91.3% of the homoglyphs and introduces only 84 new errors.

作者备注:7 pages, 2 figures, 7 tables. Accepted at the 10th International Conference on Future Networks and Distributed Systems (ICFNDS 2026), ACM ICPS. Code: https://github.com/OybekNarzullaev/byt5-uzbek-postocr

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-10 13:35 · 最新观测版本

Post-OCR Correction of Mixed-Script Uzbek Text: Byte-Level ByT5 with an Empirical Homoglyph Noise Matrix

In Uzbek official and technical documents, a large share of OCR errors is caused not by poor image quality but by characters that are visually identical across the two alphabets in use. Because the script transition is still under way, Cyrillic and Latin appear on the same page and often within a single sentence, and in our measurements the density of homoglyph errors on such pages is close to five times higher than in single-script text. We study this problem in a setting where the corpus of engineering-geological and ICT infrastructure reports may not leave the organisation, so every stage was executed on local hardware. The proposed system combines a byte-level ByT5 model with a noise generator whose sampling weights are estimated from 359 manually classified error events, together with a Levenshtein-bounded conservative decoding rule. On a Gold set of 5,204 line pairs it lowers the character error rate from 0.0578 to 0.0369, restores 91.3% of the homoglyphs and introduces only 84 new errors.

查看此版本解读 →查看此版本原文 ↗