@inproceedings{tiger-2026-overfit,
title = "To Overfit or Not to Overfit? An Evaluation of {HTR} Workflow on 17{T}h-18{T}h Century {F}rench Corpus",
author = "Tiger, Marine",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.78/",
doi = "10.63317/23hc8mveght2",
pages = "1009--1016",
abstract = "This paper presents the results of an evaluation of general Handwritten Text Recognition (HTR) models applied to 17th and 18th century corpus written in modern French and the fine-tuning of the models. Our aim was to transcribe a corpus from this period using existing pre-trained models and to assess their performance on such data. While these general models offer a large linguistic coverage, our results demonstrate they are often insufficiently adapted to the specific handwriting nuances and orthographic inconsistencies of early modern French. To improve the results, we fine-tuned a base model to develop a specialized version trained on our dataset. Although the model still encountered difficulties due to highly variable handwriting styles, it significantly improved transcription accuracy and reduced processing time. Following this step, we used a semi-automatic post-correction tool to address remaining errors and integrated Named Entity Recognition (NER) steps for automated TEI-XML encoding. This paper discusses the evaluation results of both the HTR and NER models, and how the overfitting allows to get better transcriptions on a specific corpus."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tiger-2026-overfit">
<titleInfo>
<title>To Overfit or Not to Overfit? An Evaluation of HTR Workflow on 17Th-18Th Century French Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Tiger</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the results of an evaluation of general Handwritten Text Recognition (HTR) models applied to 17th and 18th century corpus written in modern French and the fine-tuning of the models. Our aim was to transcribe a corpus from this period using existing pre-trained models and to assess their performance on such data. While these general models offer a large linguistic coverage, our results demonstrate they are often insufficiently adapted to the specific handwriting nuances and orthographic inconsistencies of early modern French. To improve the results, we fine-tuned a base model to develop a specialized version trained on our dataset. Although the model still encountered difficulties due to highly variable handwriting styles, it significantly improved transcription accuracy and reduced processing time. Following this step, we used a semi-automatic post-correction tool to address remaining errors and integrated Named Entity Recognition (NER) steps for automated TEI-XML encoding. This paper discusses the evaluation results of both the HTR and NER models, and how the overfitting allows to get better transcriptions on a specific corpus.</abstract>
<identifier type="citekey">tiger-2026-overfit</identifier>
<identifier type="doi">10.63317/23hc8mveght2</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.78/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1009</start>
<end>1016</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To Overfit or Not to Overfit? An Evaluation of HTR Workflow on 17Th-18Th Century French Corpus
%A Tiger, Marine
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F tiger-2026-overfit
%X This paper presents the results of an evaluation of general Handwritten Text Recognition (HTR) models applied to 17th and 18th century corpus written in modern French and the fine-tuning of the models. Our aim was to transcribe a corpus from this period using existing pre-trained models and to assess their performance on such data. While these general models offer a large linguistic coverage, our results demonstrate they are often insufficiently adapted to the specific handwriting nuances and orthographic inconsistencies of early modern French. To improve the results, we fine-tuned a base model to develop a specialized version trained on our dataset. Although the model still encountered difficulties due to highly variable handwriting styles, it significantly improved transcription accuracy and reduced processing time. Following this step, we used a semi-automatic post-correction tool to address remaining errors and integrated Named Entity Recognition (NER) steps for automated TEI-XML encoding. This paper discusses the evaluation results of both the HTR and NER models, and how the overfitting allows to get better transcriptions on a specific corpus.
%R 10.63317/23hc8mveght2
%U https://aclanthology.org/2026.lrec-1.78/
%U https://doi.org/10.63317/23hc8mveght2
%P 1009-1016
Markdown (Informal)
[To Overfit or Not to Overfit? An Evaluation of HTR Workflow on 17Th-18Th Century French Corpus](https://aclanthology.org/2026.lrec-1.78/) (Tiger, LREC 2026)
ACL