@inproceedings{megyesi-etal-2026-building,
title = "Building a Corpus and Database for Rare and Undeciphered Scripts",
author = {Megyesi, Beata and
Rattenborg, Rune and
L{\'a}ng, Benedek and
Waldisp{\"u}hl, Michelle and
H{\'e}der, Mih{\'a}ly},
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-1.17/",
doi = "10.63317/3w96kx3i86uo",
pages = "184--196",
abstract = "Historical sources written in rare or undeciphered scripts represent an immense but underexploited part of the world{'}s cultural and linguistic heritage. Their study is often hindered by fragmentary preservation, non-standard symbol systems, and the absence of interoperable digital resources. While recent advances in imaging, transcription, and computational analysis have improved access to historical texts, most tools rely on large quantities of labeled data and standardized encodings, requirements that are rarely met for rare or unknown writing systems. This paper presents the design and methodology of a new corpus and database dedicated to rare and undeciphered scripts worldwide. The resource integrates high-quality images, transliterations, transcriptions, linguistic annotations, and metadata within a unified data model tailored for low-resource and non-standard scripts. By adhering to FAIR principles and existing standards for linguistic and cultural heritage data, the database enables reproducible, interdisciplinary research across philology, linguistics, cryptology, and computer science. The paper outlines the data collection and digitization workflow, describes the metadata and database architecture, and demonstrates applications in analysis and decipherment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="megyesi-etal-2026-building">
<titleInfo>
<title>Building a Corpus and Database for Rare and Undeciphered Scripts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Megyesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rune</namePart>
<namePart type="family">Rattenborg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benedek</namePart>
<namePart type="family">Láng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michelle</namePart>
<namePart type="family">Waldispühl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihály</namePart>
<namePart type="family">Héder</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>Historical sources written in rare or undeciphered scripts represent an immense but underexploited part of the world’s cultural and linguistic heritage. Their study is often hindered by fragmentary preservation, non-standard symbol systems, and the absence of interoperable digital resources. While recent advances in imaging, transcription, and computational analysis have improved access to historical texts, most tools rely on large quantities of labeled data and standardized encodings, requirements that are rarely met for rare or unknown writing systems. This paper presents the design and methodology of a new corpus and database dedicated to rare and undeciphered scripts worldwide. The resource integrates high-quality images, transliterations, transcriptions, linguistic annotations, and metadata within a unified data model tailored for low-resource and non-standard scripts. By adhering to FAIR principles and existing standards for linguistic and cultural heritage data, the database enables reproducible, interdisciplinary research across philology, linguistics, cryptology, and computer science. The paper outlines the data collection and digitization workflow, describes the metadata and database architecture, and demonstrates applications in analysis and decipherment.</abstract>
<identifier type="citekey">megyesi-etal-2026-building</identifier>
<identifier type="doi">10.63317/3w96kx3i86uo</identifier>
<location>
<url>https://aclanthology.org/2026.lt4hala-1.17/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>184</start>
<end>196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a Corpus and Database for Rare and Undeciphered Scripts
%A Megyesi, Beata
%A Rattenborg, Rune
%A Láng, Benedek
%A Waldispühl, Michelle
%A Héder, Mihály
%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 megyesi-etal-2026-building
%X Historical sources written in rare or undeciphered scripts represent an immense but underexploited part of the world’s cultural and linguistic heritage. Their study is often hindered by fragmentary preservation, non-standard symbol systems, and the absence of interoperable digital resources. While recent advances in imaging, transcription, and computational analysis have improved access to historical texts, most tools rely on large quantities of labeled data and standardized encodings, requirements that are rarely met for rare or unknown writing systems. This paper presents the design and methodology of a new corpus and database dedicated to rare and undeciphered scripts worldwide. The resource integrates high-quality images, transliterations, transcriptions, linguistic annotations, and metadata within a unified data model tailored for low-resource and non-standard scripts. By adhering to FAIR principles and existing standards for linguistic and cultural heritage data, the database enables reproducible, interdisciplinary research across philology, linguistics, cryptology, and computer science. The paper outlines the data collection and digitization workflow, describes the metadata and database architecture, and demonstrates applications in analysis and decipherment.
%R 10.63317/3w96kx3i86uo
%U https://aclanthology.org/2026.lt4hala-1.17/
%U https://doi.org/10.63317/3w96kx3i86uo
%P 184-196
Markdown (Informal)
[Building a Corpus and Database for Rare and Undeciphered Scripts](https://aclanthology.org/2026.lt4hala-1.17/) (Megyesi et al., LT4HALA 2026)
ACL
- Beata Megyesi, Rune Rattenborg, Benedek Láng, Michelle Waldispühl, and Mihály Héder. 2026. Building a Corpus and Database for Rare and Undeciphered Scripts. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 184–196, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).