@inproceedings{debaene-etal-2025-evaluating,
title = "Evaluating Transformers for {OCR} Post-Correction in Early {M}odern {D}utch Theatre",
author = "Debaene, Florian and
Maladry, Aaron and
Lefever, Els and
Hoste, Veronique",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.690/",
pages = "10367--10374",
abstract = "This paper explores the effectiveness of two types of transformer models {---} large generative models and sequence-to-sequence models {---} for automatically post-correcting Optical Character Recognition (OCR) output in early modern Dutch plays. To address the need for optimally aligned data, we create a parallel dataset based on the OCRed and ground truth versions from the EmDComF corpus using state-of-the-art alignment techniques. By combining character-based and semantic methods, we design and release a qualitative OCR-to-gold parallel dataset, selecting the alignment with the lowest Character Error Rate (CER) for all alignment pairs. We then fine-tune and evaluate five generative models and four sequence-to-sequence models on the OCR post-correction dataset. Results show that sequence-to-sequence models generally outperform generative models in this task, correcting more OCR errors and overgenerating and undergenerating less, with mBART as the best performing system."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="debaene-etal-2025-evaluating">
<titleInfo>
<title>Evaluating Transformers for OCR Post-Correction in Early Modern Dutch Theatre</title>
</titleInfo>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Debaene</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Maladry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper explores the effectiveness of two types of transformer models — large generative models and sequence-to-sequence models — for automatically post-correcting Optical Character Recognition (OCR) output in early modern Dutch plays. To address the need for optimally aligned data, we create a parallel dataset based on the OCRed and ground truth versions from the EmDComF corpus using state-of-the-art alignment techniques. By combining character-based and semantic methods, we design and release a qualitative OCR-to-gold parallel dataset, selecting the alignment with the lowest Character Error Rate (CER) for all alignment pairs. We then fine-tune and evaluate five generative models and four sequence-to-sequence models on the OCR post-correction dataset. Results show that sequence-to-sequence models generally outperform generative models in this task, correcting more OCR errors and overgenerating and undergenerating less, with mBART as the best performing system.</abstract>
<identifier type="citekey">debaene-etal-2025-evaluating</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.690/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>10367</start>
<end>10374</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Transformers for OCR Post-Correction in Early Modern Dutch Theatre
%A Debaene, Florian
%A Maladry, Aaron
%A Lefever, Els
%A Hoste, Veronique
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F debaene-etal-2025-evaluating
%X This paper explores the effectiveness of two types of transformer models — large generative models and sequence-to-sequence models — for automatically post-correcting Optical Character Recognition (OCR) output in early modern Dutch plays. To address the need for optimally aligned data, we create a parallel dataset based on the OCRed and ground truth versions from the EmDComF corpus using state-of-the-art alignment techniques. By combining character-based and semantic methods, we design and release a qualitative OCR-to-gold parallel dataset, selecting the alignment with the lowest Character Error Rate (CER) for all alignment pairs. We then fine-tune and evaluate five generative models and four sequence-to-sequence models on the OCR post-correction dataset. Results show that sequence-to-sequence models generally outperform generative models in this task, correcting more OCR errors and overgenerating and undergenerating less, with mBART as the best performing system.
%U https://aclanthology.org/2025.coling-main.690/
%P 10367-10374
Markdown (Informal)
[Evaluating Transformers for OCR Post-Correction in Early Modern Dutch Theatre](https://aclanthology.org/2025.coling-main.690/) (Debaene et al., COLING 2025)
ACL