@inproceedings{lendvai-etal-2024-workflow,
title = "A Workflow for {HTR}-Postprocessing, Labeling and Classifying Diachronic and Regional Variation in Pre-{M}odern {S}lavic Texts",
author = "Lendvai, Piroska and
van Gompel, Maarten and
Jouravel, Anna and
Renje, Elena and
Reichel, Uwe and
Rabus, Achim and
Arnold, Eckhart",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.184/",
pages = "2039--2048",
abstract = "We describe ongoing work for developing a workflow for the applied use case of classifying diachronic and regional language variation in Pre-Modern Slavic texts. The data were obtained via handwritten text recognition (HTR) on medieval manuscripts and printings and partly by manual transcription. Our goal is to develop a workflow for such historical language data, covering HTR-postprocessing, annotating and classifying the digitized texts. We test and adapt existing language resources to fit the pipeline with low-barrier tooling, accessible for Humanists with limited experience in research data infrastructures, computational analysis or advanced methods of natural language processing (NLP). The workflow starts by addressing ground truth (GT) data creation for diagnosing and correcting HTR errors via string metrics and data-driven methods. On GT and on HTR data, we subsequently show classification results using transfer learning on sentence-level text snippets. Next, we report on our token-level data labeling efforts. Each step of the workflow is complemented with describing current limitations and our corresponding work in progress."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lendvai-etal-2024-workflow">
<titleInfo>
<title>A Workflow for HTR-Postprocessing, Labeling and Classifying Diachronic and Regional Variation in Pre-Modern Slavic Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piroska</namePart>
<namePart type="family">Lendvai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarten</namePart>
<namePart type="family">van Gompel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Jouravel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Renje</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uwe</namePart>
<namePart type="family">Reichel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Achim</namePart>
<namePart type="family">Rabus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eckhart</namePart>
<namePart type="family">Arnold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe ongoing work for developing a workflow for the applied use case of classifying diachronic and regional language variation in Pre-Modern Slavic texts. The data were obtained via handwritten text recognition (HTR) on medieval manuscripts and printings and partly by manual transcription. Our goal is to develop a workflow for such historical language data, covering HTR-postprocessing, annotating and classifying the digitized texts. We test and adapt existing language resources to fit the pipeline with low-barrier tooling, accessible for Humanists with limited experience in research data infrastructures, computational analysis or advanced methods of natural language processing (NLP). The workflow starts by addressing ground truth (GT) data creation for diagnosing and correcting HTR errors via string metrics and data-driven methods. On GT and on HTR data, we subsequently show classification results using transfer learning on sentence-level text snippets. Next, we report on our token-level data labeling efforts. Each step of the workflow is complemented with describing current limitations and our corresponding work in progress.</abstract>
<identifier type="citekey">lendvai-etal-2024-workflow</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.184/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2039</start>
<end>2048</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Workflow for HTR-Postprocessing, Labeling and Classifying Diachronic and Regional Variation in Pre-Modern Slavic Texts
%A Lendvai, Piroska
%A van Gompel, Maarten
%A Jouravel, Anna
%A Renje, Elena
%A Reichel, Uwe
%A Rabus, Achim
%A Arnold, Eckhart
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F lendvai-etal-2024-workflow
%X We describe ongoing work for developing a workflow for the applied use case of classifying diachronic and regional language variation in Pre-Modern Slavic texts. The data were obtained via handwritten text recognition (HTR) on medieval manuscripts and printings and partly by manual transcription. Our goal is to develop a workflow for such historical language data, covering HTR-postprocessing, annotating and classifying the digitized texts. We test and adapt existing language resources to fit the pipeline with low-barrier tooling, accessible for Humanists with limited experience in research data infrastructures, computational analysis or advanced methods of natural language processing (NLP). The workflow starts by addressing ground truth (GT) data creation for diagnosing and correcting HTR errors via string metrics and data-driven methods. On GT and on HTR data, we subsequently show classification results using transfer learning on sentence-level text snippets. Next, we report on our token-level data labeling efforts. Each step of the workflow is complemented with describing current limitations and our corresponding work in progress.
%U https://aclanthology.org/2024.lrec-main.184/
%P 2039-2048
Markdown (Informal)
[A Workflow for HTR-Postprocessing, Labeling and Classifying Diachronic and Regional Variation in Pre-Modern Slavic Texts](https://aclanthology.org/2024.lrec-main.184/) (Lendvai et al., LREC-COLING 2024)
ACL
- Piroska Lendvai, Maarten van Gompel, Anna Jouravel, Elena Renje, Uwe Reichel, Achim Rabus, and Eckhart Arnold. 2024. A Workflow for HTR-Postprocessing, Labeling and Classifying Diachronic and Regional Variation in Pre-Modern Slavic Texts. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 2039–2048, Torino, Italia. ELRA and ICCL.