@inproceedings{gordin-etal-2024-cured,
title = "{C}u{R}e{D}: Deep Learning Optical Character Recognition for Cuneiform Text Editions and Legacy Materials",
author = "Gordin, Shai and
Alper, Morris and
Romach, Avital and
Saenz Santos, Luis and
Yochai, Naama and
Lalazar, Roey",
editor = "Pavlopoulos, John and
Sommerschield, Thea and
Assael, Yannis and
Gordin, Shai and
Cho, Kyunghyun and
Passarotti, Marco and
Sprugnoli, Rachele and
Liu, Yudong and
Li, Bin and
Anderson, Adam",
booktitle = "Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)",
month = aug,
year = "2024",
address = "Hybrid in Bangkok, Thailand and online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.ml4al-1.14/",
doi = "10.18653/v1/2024.ml4al-1.14",
pages = "130--140",
abstract = "Cuneiform documents, the earliest known form of writing, are prolific textual sources of the ancient past. Experts publish editions of these texts in transliteration using specialized typesetting, but most remain inaccessible for computational analysis in traditional printed books or legacy materials. Off-the-shelf OCR systems are insufficient for digitization without adaptation. We present CuReD (Cuneiform Recognition-Documents), a deep learning-based human-in-the-loop OCR pipeline for digitizing scanned transliterations of cuneiform texts. CuReD has a character error rate of 9{\%} on clean data and 11{\%} on representative scans. We digitized a challenging sample of transliterated cuneiform documents, as well as lexical index cards from the University of Pennsylvania Museum, demonstrating the feasibility of our platform for enabling computational analysis and bolstering machine-readable cuneiform text datasets. Our result provide the first human-in-the-loop pipeline and interface for digitizing transliterated cuneiform sources and legacy materials, enabling the enrichment of digital sources of these low-resource languages."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gordin-etal-2024-cured">
<titleInfo>
<title>CuReD: Deep Learning Optical Character Recognition for Cuneiform Text Editions and Legacy Materials</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Gordin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Morris</namePart>
<namePart type="family">Alper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avital</namePart>
<namePart type="family">Romach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Saenz Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naama</namePart>
<namePart type="family">Yochai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roey</namePart>
<namePart type="family">Lalazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Pavlopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thea</namePart>
<namePart type="family">Sommerschield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yannis</namePart>
<namePart type="family">Assael</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Gordin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</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>
<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">Yudong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid in Bangkok, Thailand and online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cuneiform documents, the earliest known form of writing, are prolific textual sources of the ancient past. Experts publish editions of these texts in transliteration using specialized typesetting, but most remain inaccessible for computational analysis in traditional printed books or legacy materials. Off-the-shelf OCR systems are insufficient for digitization without adaptation. We present CuReD (Cuneiform Recognition-Documents), a deep learning-based human-in-the-loop OCR pipeline for digitizing scanned transliterations of cuneiform texts. CuReD has a character error rate of 9% on clean data and 11% on representative scans. We digitized a challenging sample of transliterated cuneiform documents, as well as lexical index cards from the University of Pennsylvania Museum, demonstrating the feasibility of our platform for enabling computational analysis and bolstering machine-readable cuneiform text datasets. Our result provide the first human-in-the-loop pipeline and interface for digitizing transliterated cuneiform sources and legacy materials, enabling the enrichment of digital sources of these low-resource languages.</abstract>
<identifier type="citekey">gordin-etal-2024-cured</identifier>
<identifier type="doi">10.18653/v1/2024.ml4al-1.14</identifier>
<location>
<url>https://aclanthology.org/2024.ml4al-1.14/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>130</start>
<end>140</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CuReD: Deep Learning Optical Character Recognition for Cuneiform Text Editions and Legacy Materials
%A Gordin, Shai
%A Alper, Morris
%A Romach, Avital
%A Saenz Santos, Luis
%A Yochai, Naama
%A Lalazar, Roey
%Y Pavlopoulos, John
%Y Sommerschield, Thea
%Y Assael, Yannis
%Y Gordin, Shai
%Y Cho, Kyunghyun
%Y Passarotti, Marco
%Y Sprugnoli, Rachele
%Y Liu, Yudong
%Y Li, Bin
%Y Anderson, Adam
%S Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Hybrid in Bangkok, Thailand and online
%F gordin-etal-2024-cured
%X Cuneiform documents, the earliest known form of writing, are prolific textual sources of the ancient past. Experts publish editions of these texts in transliteration using specialized typesetting, but most remain inaccessible for computational analysis in traditional printed books or legacy materials. Off-the-shelf OCR systems are insufficient for digitization without adaptation. We present CuReD (Cuneiform Recognition-Documents), a deep learning-based human-in-the-loop OCR pipeline for digitizing scanned transliterations of cuneiform texts. CuReD has a character error rate of 9% on clean data and 11% on representative scans. We digitized a challenging sample of transliterated cuneiform documents, as well as lexical index cards from the University of Pennsylvania Museum, demonstrating the feasibility of our platform for enabling computational analysis and bolstering machine-readable cuneiform text datasets. Our result provide the first human-in-the-loop pipeline and interface for digitizing transliterated cuneiform sources and legacy materials, enabling the enrichment of digital sources of these low-resource languages.
%R 10.18653/v1/2024.ml4al-1.14
%U https://aclanthology.org/2024.ml4al-1.14/
%U https://doi.org/10.18653/v1/2024.ml4al-1.14
%P 130-140
Markdown (Informal)
[CuReD: Deep Learning Optical Character Recognition for Cuneiform Text Editions and Legacy Materials](https://aclanthology.org/2024.ml4al-1.14/) (Gordin et al., ML4AL 2024)
ACL