@inproceedings{strobel-etal-2020-much,
title = "How Much Data Do You Need? About the Creation of a Ground Truth for Black Letter and the Effectiveness of Neural {OCR}",
author = {Str{\"o}bel, Phillip Benjamin and
Clematide, Simon and
Volk, Martin},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.436",
pages = "3551--3559",
abstract = "Recent advances in Optical Character Recognition (OCR) and Handwritten Text Recognition (HTR) have led to more accurate textrecognition of historical documents. The Digital Humanities heavily profit from these developments, but they still struggle whenchoosing from the plethora of OCR systems available on the one hand and when defining workflows for their projects on the other hand. In this work, we present our approach to build a ground truth for a historical German-language newspaper published in black letter. Wealso report how we used it to systematically evaluate the performance of different OCR engines. Additionally, we used this ground truthto make an informed estimate as to how much data is necessary to achieve high-quality OCR results. The outcomes of our experimentsshow that HTR architectures can successfully recognise black letter text and that a ground truth size of 50 newspaper pages suffices toachieve good OCR accuracy. Moreover, our models perform equally well on data they have not seen during training, which means thatadditional manual correction for diverging data is superfluous.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strobel-etal-2020-much">
<titleInfo>
<title>How Much Data Do You Need? About the Creation of a Ground Truth for Black Letter and the Effectiveness of Neural OCR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Phillip</namePart>
<namePart type="given">Benjamin</namePart>
<namePart type="family">Ströbel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Clematide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Volk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Recent advances in Optical Character Recognition (OCR) and Handwritten Text Recognition (HTR) have led to more accurate textrecognition of historical documents. The Digital Humanities heavily profit from these developments, but they still struggle whenchoosing from the plethora of OCR systems available on the one hand and when defining workflows for their projects on the other hand. In this work, we present our approach to build a ground truth for a historical German-language newspaper published in black letter. Wealso report how we used it to systematically evaluate the performance of different OCR engines. Additionally, we used this ground truthto make an informed estimate as to how much data is necessary to achieve high-quality OCR results. The outcomes of our experimentsshow that HTR architectures can successfully recognise black letter text and that a ground truth size of 50 newspaper pages suffices toachieve good OCR accuracy. Moreover, our models perform equally well on data they have not seen during training, which means thatadditional manual correction for diverging data is superfluous.</abstract>
<identifier type="citekey">strobel-etal-2020-much</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.436</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3551</start>
<end>3559</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Much Data Do You Need? About the Creation of a Ground Truth for Black Letter and the Effectiveness of Neural OCR
%A Ströbel, Phillip Benjamin
%A Clematide, Simon
%A Volk, Martin
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F strobel-etal-2020-much
%X Recent advances in Optical Character Recognition (OCR) and Handwritten Text Recognition (HTR) have led to more accurate textrecognition of historical documents. The Digital Humanities heavily profit from these developments, but they still struggle whenchoosing from the plethora of OCR systems available on the one hand and when defining workflows for their projects on the other hand. In this work, we present our approach to build a ground truth for a historical German-language newspaper published in black letter. Wealso report how we used it to systematically evaluate the performance of different OCR engines. Additionally, we used this ground truthto make an informed estimate as to how much data is necessary to achieve high-quality OCR results. The outcomes of our experimentsshow that HTR architectures can successfully recognise black letter text and that a ground truth size of 50 newspaper pages suffices toachieve good OCR accuracy. Moreover, our models perform equally well on data they have not seen during training, which means thatadditional manual correction for diverging data is superfluous.
%U https://aclanthology.org/2020.lrec-1.436
%P 3551-3559
Markdown (Informal)
[How Much Data Do You Need? About the Creation of a Ground Truth for Black Letter and the Effectiveness of Neural OCR](https://aclanthology.org/2020.lrec-1.436) (Ströbel et al., LREC 2020)
ACL