@inproceedings{jasonarson-etal-2023-generating,
title = "Generating Errors: {OCR} Post-Processing for {I}celandic",
author = "Jasonarson, Atli and
Steingr{\'\i}msson, Stein{\th}{\'o}r and
Sigur{\dh}sson, Einar and
Magn{\'u}sson, {\'A}rni and
Ingimundarson, Finnur",
editor = {Alum{\"a}e, Tanel and
Fishel, Mark},
booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may,
year = "2023",
address = "T{\'o}rshavn, Faroe Islands",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2023.nodalida-1.29",
pages = "286--291",
abstract = "We describe work on enhancing the performance of transformer-based encoder-decoder models for OCR post-correction on modern and historical Icelandic texts, where OCRed data are scarce. We trained six models, four from scratch and two fine-tuned versions of Google{'}s ByT5, on a combination of real data and texts populated with artificially generated errors. Our results show that the models trained from scratch, as opposed to the fine-tuned versions, benefited the most from the addition of artificially generated errors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jasonarson-etal-2023-generating">
<titleInfo>
<title>Generating Errors: OCR Post-Processing for Icelandic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atli</namePart>
<namePart type="family">Jasonarson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stein\thór</namePart>
<namePart type="family">Steingrímsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Einar</namePart>
<namePart type="family">Sigur\dhsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Árni</namePart>
<namePart type="family">Magnússon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Finnur</namePart>
<namePart type="family">Ingimundarson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanel</namePart>
<namePart type="family">Alumäe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tórshavn, Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe work on enhancing the performance of transformer-based encoder-decoder models for OCR post-correction on modern and historical Icelandic texts, where OCRed data are scarce. We trained six models, four from scratch and two fine-tuned versions of Google’s ByT5, on a combination of real data and texts populated with artificially generated errors. Our results show that the models trained from scratch, as opposed to the fine-tuned versions, benefited the most from the addition of artificially generated errors.</abstract>
<identifier type="citekey">jasonarson-etal-2023-generating</identifier>
<location>
<url>https://aclanthology.org/2023.nodalida-1.29</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>286</start>
<end>291</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Errors: OCR Post-Processing for Icelandic
%A Jasonarson, Atli
%A Steingrímsson, Stein\thór
%A Sigur\dhsson, Einar
%A Magnússon, Árni
%A Ingimundarson, Finnur
%Y Alumäe, Tanel
%Y Fishel, Mark
%S Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2023
%8 May
%I University of Tartu Library
%C Tórshavn, Faroe Islands
%F jasonarson-etal-2023-generating
%X We describe work on enhancing the performance of transformer-based encoder-decoder models for OCR post-correction on modern and historical Icelandic texts, where OCRed data are scarce. We trained six models, four from scratch and two fine-tuned versions of Google’s ByT5, on a combination of real data and texts populated with artificially generated errors. Our results show that the models trained from scratch, as opposed to the fine-tuned versions, benefited the most from the addition of artificially generated errors.
%U https://aclanthology.org/2023.nodalida-1.29
%P 286-291
Markdown (Informal)
[Generating Errors: OCR Post-Processing for Icelandic](https://aclanthology.org/2023.nodalida-1.29) (Jasonarson et al., NoDaLiDa 2023)
ACL
- Atli Jasonarson, Steinþór Steingrímsson, Einar Sigurðsson, Árni Magnússon, and Finnur Ingimundarson. 2023. Generating Errors: OCR Post-Processing for Icelandic. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 286–291, Tórshavn, Faroe Islands. University of Tartu Library.