@inproceedings{wang-etal-2026-overview,
title = "Overview of {E}va{H}an2026: The First International Evaluation of {A}ncient {C}hinese {OCR} and Layout Analysis",
author = "Wang, Dongbo and
Zhu, Dongmei and
Li, Jieqiong and
Liu, Chang and
Wu, Ruifeng and
Yang, Fan and
Yue, Zhu and
Gao, Xin and
Zhixiao, Zhao and
Zhao, Xue and
Wu, Zhongzheng and
Liu, Liu and
Bin, Li",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages ({LT}4{HALA} 2026) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.lt4hala-1.23/",
doi = "10.63317/3a35qx3n2fg9",
pages = "244--262",
abstract = "Ancient Chinese documents are vital for historical research, necessitating high-precision character recognition and layout analysis for digitization. This paper introduces EvaHan2026, the inaugural international shared task for simultaneous optical character recognition and layout parsing of ancient texts. The evaluation framework comprehensively assesses model performance across diverse calligraphic styles and complex structures, including main body text, interlinear annotations, and illustrations. Among thirteen participating teams, four successfully completed all tasks within the closed track. Experimental results reveal that character recognition accuracy reached 97.36{\%} on engraved texts (Test Set A) and 95.71{\%} on handwritten texts (Test Set C) when accounting for character variants. For layout recognition in complex layouts (Test Set B), the best team achieved a peak mean Average Precision (mAP) of 59.41{\%} and an Intersection over Union (loU) of 76.38{\%}. Our analysis indicates that calligraphic variability, layout density, and character variants significantly modulate system performance. Consequently, enhancing robustness within complex layouts and developing synergistic models that integrate textual and structural information remain primary challenges for intelligent interpretation of ancient writings ."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-overview">
<titleInfo>
<title>Overview of EvaHan2026: The First International Evaluation of Ancient Chinese OCR and Layout Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongbo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongmei</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieqiong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fan</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Yue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Zhixiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xue</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongzheng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Bin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Ancient Chinese documents are vital for historical research, necessitating high-precision character recognition and layout analysis for digitization. This paper introduces EvaHan2026, the inaugural international shared task for simultaneous optical character recognition and layout parsing of ancient texts. The evaluation framework comprehensively assesses model performance across diverse calligraphic styles and complex structures, including main body text, interlinear annotations, and illustrations. Among thirteen participating teams, four successfully completed all tasks within the closed track. Experimental results reveal that character recognition accuracy reached 97.36% on engraved texts (Test Set A) and 95.71% on handwritten texts (Test Set C) when accounting for character variants. For layout recognition in complex layouts (Test Set B), the best team achieved a peak mean Average Precision (mAP) of 59.41% and an Intersection over Union (loU) of 76.38%. Our analysis indicates that calligraphic variability, layout density, and character variants significantly modulate system performance. Consequently, enhancing robustness within complex layouts and developing synergistic models that integrate textual and structural information remain primary challenges for intelligent interpretation of ancient writings .</abstract>
<identifier type="citekey">wang-etal-2026-overview</identifier>
<identifier type="doi">10.63317/3a35qx3n2fg9</identifier>
<location>
<url>https://aclanthology.org/2026.lt4hala-1.23/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>244</start>
<end>262</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overview of EvaHan2026: The First International Evaluation of Ancient Chinese OCR and Layout Analysis
%A Wang, Dongbo
%A Zhu, Dongmei
%A Li, Jieqiong
%A Liu, Chang
%A Wu, Ruifeng
%A Yang, Fan
%A Yue, Zhu
%A Gao, Xin
%A Zhixiao, Zhao
%A Zhao, Xue
%A Wu, Zhongzheng
%A Liu, Liu
%A Bin, Li
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F wang-etal-2026-overview
%X Ancient Chinese documents are vital for historical research, necessitating high-precision character recognition and layout analysis for digitization. This paper introduces EvaHan2026, the inaugural international shared task for simultaneous optical character recognition and layout parsing of ancient texts. The evaluation framework comprehensively assesses model performance across diverse calligraphic styles and complex structures, including main body text, interlinear annotations, and illustrations. Among thirteen participating teams, four successfully completed all tasks within the closed track. Experimental results reveal that character recognition accuracy reached 97.36% on engraved texts (Test Set A) and 95.71% on handwritten texts (Test Set C) when accounting for character variants. For layout recognition in complex layouts (Test Set B), the best team achieved a peak mean Average Precision (mAP) of 59.41% and an Intersection over Union (loU) of 76.38%. Our analysis indicates that calligraphic variability, layout density, and character variants significantly modulate system performance. Consequently, enhancing robustness within complex layouts and developing synergistic models that integrate textual and structural information remain primary challenges for intelligent interpretation of ancient writings .
%R 10.63317/3a35qx3n2fg9
%U https://aclanthology.org/2026.lt4hala-1.23/
%U https://doi.org/10.63317/3a35qx3n2fg9
%P 244-262
Markdown (Informal)
[Overview of EvaHan2026: The First International Evaluation of Ancient Chinese OCR and Layout Analysis](https://aclanthology.org/2026.lt4hala-1.23/) (Wang et al., LT4HALA 2026)
ACL
- Dongbo Wang, Dongmei Zhu, Jieqiong Li, Chang Liu, Ruifeng Wu, Fan Yang, Zhu Yue, Xin Gao, Zhao Zhixiao, Xue Zhao, Zhongzheng Wu, Liu Liu, and Li Bin. 2026. Overview of EvaHan2026: The First International Evaluation of Ancient Chinese OCR and Layout Analysis. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 244–262, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).