@inproceedings{backer-hyman-2025-bootstrapping,
title = "Bootstrapping {AI}: Interdisciplinary Approaches to Assessing {OCR} Quality in {E}nglish-Language Historical Documents",
author = "Backer, Samuel and
Hyman, Louis",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Bizzoni, Yuri and
Miyagawa, So and
Alnajjar, Khalid},
booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
month = may,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.nlp4dh-1.21/",
doi = "10.18653/v1/2025.nlp4dh-1.21",
pages = "251--256",
ISBN = "979-8-89176-234-3",
abstract = "New LLM-based OCR and post-OCR correction methods promise to transform computational historical research, yet their efficacy remains contested. We compare multiple correction approaches, including methods for ``bootstrapping'' fine-tuning with LLM-generated data, and measure their effect on downstream tasks. Our results suggest that standard OCR metrics often underestimate performance gains for historical research, underscoring the need for discipline-driven evaluations that can better reflect the needs of computational humanists."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="backer-hyman-2025-bootstrapping">
<titleInfo>
<title>Bootstrapping AI: Interdisciplinary Approaches to Assessing OCR Quality in English-Language Historical Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Backer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis</namePart>
<namePart type="family">Hyman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-234-3</identifier>
</relatedItem>
<abstract>New LLM-based OCR and post-OCR correction methods promise to transform computational historical research, yet their efficacy remains contested. We compare multiple correction approaches, including methods for “bootstrapping” fine-tuning with LLM-generated data, and measure their effect on downstream tasks. Our results suggest that standard OCR metrics often underestimate performance gains for historical research, underscoring the need for discipline-driven evaluations that can better reflect the needs of computational humanists.</abstract>
<identifier type="citekey">backer-hyman-2025-bootstrapping</identifier>
<identifier type="doi">10.18653/v1/2025.nlp4dh-1.21</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4dh-1.21/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>251</start>
<end>256</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bootstrapping AI: Interdisciplinary Approaches to Assessing OCR Quality in English-Language Historical Documents
%A Backer, Samuel
%A Hyman, Louis
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Bizzoni, Yuri
%Y Miyagawa, So
%Y Alnajjar, Khalid
%S Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-234-3
%F backer-hyman-2025-bootstrapping
%X New LLM-based OCR and post-OCR correction methods promise to transform computational historical research, yet their efficacy remains contested. We compare multiple correction approaches, including methods for “bootstrapping” fine-tuning with LLM-generated data, and measure their effect on downstream tasks. Our results suggest that standard OCR metrics often underestimate performance gains for historical research, underscoring the need for discipline-driven evaluations that can better reflect the needs of computational humanists.
%R 10.18653/v1/2025.nlp4dh-1.21
%U https://aclanthology.org/2025.nlp4dh-1.21/
%U https://doi.org/10.18653/v1/2025.nlp4dh-1.21
%P 251-256
Markdown (Informal)
[Bootstrapping AI: Interdisciplinary Approaches to Assessing OCR Quality in English-Language Historical Documents](https://aclanthology.org/2025.nlp4dh-1.21/) (Backer & Hyman, NLP4DH 2025)
ACL