@inproceedings{zhang-etal-2026-explainable,
title = "Explainable Coarse-to-Fine Ancient Manuscript Duplicates Discovery",
author = "Zhang, Chongsheng and
Wu, Shuwen and
Chen, Yingqi and
Men, Yi and
Fan, Gaojuan and
Jiang, Yubin and
A{\ss}enmacher, Matthias and
Heumann, Christian",
editor = "Agrawal, Sweta and
Abad, Alberto",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-demos.23/",
pages = "235--241",
ISBN = "979-8-89176-461-3",
abstract = "Ancient manuscripts are the primary source of ancient linguistic corpora. However, some of them exhibit duplications due to unintentional repeated publication or deliberate forgery. Notable examples include counterfeit fragments within the Dead Sea Scrolls and the repeated publication of Oracle Bones (OB). Identifying such duplicates is critical for both archaeological curation and historical research. We present OBD-Finder, an explainable coarse-to-fine framework for large-scale duplicate discovery in ancient manuscript collections, with a primary focus on Oracle Bones. OBD-Finder integrates unsupervised low-level keypoint matching with high-level character-centric content similarity to progressively filter and rank duplicate candidates, balancing retrieval accuracy with computational efficiency. Designed as a practical, transparent, and domain-expert-friendly tool, the system produces candidate duplicates and supports expert inspection and validation. In real-world deployment, OBD-Finder has enabled domain experts to uncover 63 previously unknown duplicate Oracle Bone pairs that had remained overlooked for decades. Extensive experiments also confirm that OBD-Finder achieves competitive retrieval accuracy while offering substantially superior efficiency and interpretability compared to existing approaches. Code and deployed system are publicly available: https://github.com/cszhangLMU/OBD-Finder/."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-explainable">
<titleInfo>
<title>Explainable Coarse-to-Fine Ancient Manuscript Duplicates Discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chongsheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuwen</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingqi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Men</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaojuan</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Aßenmacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Heumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Abad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-461-3</identifier>
</relatedItem>
<abstract>Ancient manuscripts are the primary source of ancient linguistic corpora. However, some of them exhibit duplications due to unintentional repeated publication or deliberate forgery. Notable examples include counterfeit fragments within the Dead Sea Scrolls and the repeated publication of Oracle Bones (OB). Identifying such duplicates is critical for both archaeological curation and historical research. We present OBD-Finder, an explainable coarse-to-fine framework for large-scale duplicate discovery in ancient manuscript collections, with a primary focus on Oracle Bones. OBD-Finder integrates unsupervised low-level keypoint matching with high-level character-centric content similarity to progressively filter and rank duplicate candidates, balancing retrieval accuracy with computational efficiency. Designed as a practical, transparent, and domain-expert-friendly tool, the system produces candidate duplicates and supports expert inspection and validation. In real-world deployment, OBD-Finder has enabled domain experts to uncover 63 previously unknown duplicate Oracle Bone pairs that had remained overlooked for decades. Extensive experiments also confirm that OBD-Finder achieves competitive retrieval accuracy while offering substantially superior efficiency and interpretability compared to existing approaches. Code and deployed system are publicly available: https://github.com/cszhangLMU/OBD-Finder/.</abstract>
<identifier type="citekey">zhang-etal-2026-explainable</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-demos.23/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>235</start>
<end>241</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Explainable Coarse-to-Fine Ancient Manuscript Duplicates Discovery
%A Zhang, Chongsheng
%A Wu, Shuwen
%A Chen, Yingqi
%A Men, Yi
%A Fan, Gaojuan
%A Jiang, Yubin
%A Aßenmacher, Matthias
%A Heumann, Christian
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F zhang-etal-2026-explainable
%X Ancient manuscripts are the primary source of ancient linguistic corpora. However, some of them exhibit duplications due to unintentional repeated publication or deliberate forgery. Notable examples include counterfeit fragments within the Dead Sea Scrolls and the repeated publication of Oracle Bones (OB). Identifying such duplicates is critical for both archaeological curation and historical research. We present OBD-Finder, an explainable coarse-to-fine framework for large-scale duplicate discovery in ancient manuscript collections, with a primary focus on Oracle Bones. OBD-Finder integrates unsupervised low-level keypoint matching with high-level character-centric content similarity to progressively filter and rank duplicate candidates, balancing retrieval accuracy with computational efficiency. Designed as a practical, transparent, and domain-expert-friendly tool, the system produces candidate duplicates and supports expert inspection and validation. In real-world deployment, OBD-Finder has enabled domain experts to uncover 63 previously unknown duplicate Oracle Bone pairs that had remained overlooked for decades. Extensive experiments also confirm that OBD-Finder achieves competitive retrieval accuracy while offering substantially superior efficiency and interpretability compared to existing approaches. Code and deployed system are publicly available: https://github.com/cszhangLMU/OBD-Finder/.
%U https://aclanthology.org/2026.emnlp-demos.23/
%P 235-241
Markdown (Informal)
[Explainable Coarse-to-Fine Ancient Manuscript Duplicates Discovery](https://aclanthology.org/2026.emnlp-demos.23/) (Zhang et al., EMNLP 2026)
ACL
- Chongsheng Zhang, Shuwen Wu, Yingqi Chen, Yi Men, Gaojuan Fan, Yubin Jiang, Matthias Aßenmacher, and Christian Heumann. 2026. Explainable Coarse-to-Fine Ancient Manuscript Duplicates Discovery. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 235–241, Budapest, Hungary. Association for Computational Linguistics.