@inproceedings{fan-etal-2026-dual,
title = "A Dual-Modality Framework for Ancient Document Layout Analysis and Text Recognition",
author = "Fan, Qi and
Hu, Jieming and
Ye, Chen",
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-1.27/",
doi = "10.63317/4snk2mjgyxyd",
pages = "277--287",
abstract = "The digital preservation of ancient Chinese literature requires robust capabilities spanning layout analysis and text recognition. This paper presents a comprehensive framework addressing two fundamental challenges: (1) Layout Element Analysis (Task B) for detecting page elements (text, image, book{\_}edge, seal) amidst degradation, nested structures, and extreme class imbalance; and (2) Text Recognition (Tasks A {\&} C) for end-to-end transcription of printed and handwritten classical documents. For layout analysis, we propose a dual-modality solution. The Closed Modality formulates this as a sequence-to-sequence problem using Vision-Language Models (VLMs), introducing spatial discretization tokenization and a Frequency-Aware Sequential Curriculum Learning framework with dynamic memory replay. The Open Modality presents HistLayout-DETR, a set prediction architecture integrating an Augmented Morphological Encoder and a Polygon Boundary Refinement head. For text recognition, we formulate OCR as a domain-constrained visual language generation task using Qwen2.5-VL with LoRA fine-tuning. We employ structured prompts encoding reading order and Traditional Chinese character preservation across domains. Extensive experiments on the EvaHan 2026 dataset validate our framework{'}s superiority. In layout analysis, our curriculum-guided paradigm achieves a Macro F1 of 0.7992 and mAP@[.5:.95] of 0.5438. In text recognition, we achieve CERs of 0.0271 on printed and 0.0433 on handwritten texts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fan-etal-2026-dual">
<titleInfo>
<title>A Dual-Modality Framework for Ancient Document Layout Analysis and Text Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieming</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Ye</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>The digital preservation of ancient Chinese literature requires robust capabilities spanning layout analysis and text recognition. This paper presents a comprehensive framework addressing two fundamental challenges: (1) Layout Element Analysis (Task B) for detecting page elements (text, image, book_edge, seal) amidst degradation, nested structures, and extreme class imbalance; and (2) Text Recognition (Tasks A & C) for end-to-end transcription of printed and handwritten classical documents. For layout analysis, we propose a dual-modality solution. The Closed Modality formulates this as a sequence-to-sequence problem using Vision-Language Models (VLMs), introducing spatial discretization tokenization and a Frequency-Aware Sequential Curriculum Learning framework with dynamic memory replay. The Open Modality presents HistLayout-DETR, a set prediction architecture integrating an Augmented Morphological Encoder and a Polygon Boundary Refinement head. For text recognition, we formulate OCR as a domain-constrained visual language generation task using Qwen2.5-VL with LoRA fine-tuning. We employ structured prompts encoding reading order and Traditional Chinese character preservation across domains. Extensive experiments on the EvaHan 2026 dataset validate our framework’s superiority. In layout analysis, our curriculum-guided paradigm achieves a Macro F1 of 0.7992 and mAP@[.5:.95] of 0.5438. In text recognition, we achieve CERs of 0.0271 on printed and 0.0433 on handwritten texts.</abstract>
<identifier type="citekey">fan-etal-2026-dual</identifier>
<identifier type="doi">10.63317/4snk2mjgyxyd</identifier>
<location>
<url>https://aclanthology.org/2026.lt4hala-1.27/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>277</start>
<end>287</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dual-Modality Framework for Ancient Document Layout Analysis and Text Recognition
%A Fan, Qi
%A Hu, Jieming
%A Ye, Chen
%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 fan-etal-2026-dual
%X The digital preservation of ancient Chinese literature requires robust capabilities spanning layout analysis and text recognition. This paper presents a comprehensive framework addressing two fundamental challenges: (1) Layout Element Analysis (Task B) for detecting page elements (text, image, book_edge, seal) amidst degradation, nested structures, and extreme class imbalance; and (2) Text Recognition (Tasks A & C) for end-to-end transcription of printed and handwritten classical documents. For layout analysis, we propose a dual-modality solution. The Closed Modality formulates this as a sequence-to-sequence problem using Vision-Language Models (VLMs), introducing spatial discretization tokenization and a Frequency-Aware Sequential Curriculum Learning framework with dynamic memory replay. The Open Modality presents HistLayout-DETR, a set prediction architecture integrating an Augmented Morphological Encoder and a Polygon Boundary Refinement head. For text recognition, we formulate OCR as a domain-constrained visual language generation task using Qwen2.5-VL with LoRA fine-tuning. We employ structured prompts encoding reading order and Traditional Chinese character preservation across domains. Extensive experiments on the EvaHan 2026 dataset validate our framework’s superiority. In layout analysis, our curriculum-guided paradigm achieves a Macro F1 of 0.7992 and mAP@[.5:.95] of 0.5438. In text recognition, we achieve CERs of 0.0271 on printed and 0.0433 on handwritten texts.
%R 10.63317/4snk2mjgyxyd
%U https://aclanthology.org/2026.lt4hala-1.27/
%U https://doi.org/10.63317/4snk2mjgyxyd
%P 277-287
Markdown (Informal)
[A Dual-Modality Framework for Ancient Document Layout Analysis and Text Recognition](https://aclanthology.org/2026.lt4hala-1.27/) (Fan et al., LT4HALA 2026)
ACL