@inproceedings{clematide-etal-2016-crowdsourcing,
title = "Crowdsourcing an {OCR} Gold Standard for a {G}erman and {F}rench Heritage Corpus",
author = "Clematide, Simon and
Furrer, Lenz and
Volk, Martin",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1155",
pages = "975--982",
abstract = "Crowdsourcing approaches for post-correction of OCR output (Optical Character Recognition) have been successfully applied to several historic text collections. We report on our crowd-correction platform Kokos, which we built to improve the OCR quality of the digitized yearbooks of the Swiss Alpine Club (SAC) from the 19th century. This multilingual heritage corpus consists of Alpine texts mainly written in German and French, all typeset in Antiqua font. Finding and engaging volunteers for correcting large amounts of pages into high quality text requires a carefully designed user interface, an easy-to-use workflow, and continuous efforts for keeping the participants motivated. More than 180,000 characters on about 21,000 pages were corrected by volunteers in about 7 month, achieving an OCR gold standard with a systematically evaluated accuracy of 99.7{\%} on the word level. The crowdsourced OCR gold standard and the corresponding original OCR recognition results from Abby FineReader 7 for each page are available as a resource. Additionally, the scanned images (300dpi) of all pages are included in order to facilitate tests with other OCR software.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="clematide-etal-2016-crowdsourcing">
<titleInfo>
<title>Crowdsourcing an OCR Gold Standard for a German and French Heritage Corpus</title>
</titleInfo>
<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">Lenz</namePart>
<namePart type="family">Furrer</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>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Crowdsourcing approaches for post-correction of OCR output (Optical Character Recognition) have been successfully applied to several historic text collections. We report on our crowd-correction platform Kokos, which we built to improve the OCR quality of the digitized yearbooks of the Swiss Alpine Club (SAC) from the 19th century. This multilingual heritage corpus consists of Alpine texts mainly written in German and French, all typeset in Antiqua font. Finding and engaging volunteers for correcting large amounts of pages into high quality text requires a carefully designed user interface, an easy-to-use workflow, and continuous efforts for keeping the participants motivated. More than 180,000 characters on about 21,000 pages were corrected by volunteers in about 7 month, achieving an OCR gold standard with a systematically evaluated accuracy of 99.7% on the word level. The crowdsourced OCR gold standard and the corresponding original OCR recognition results from Abby FineReader 7 for each page are available as a resource. Additionally, the scanned images (300dpi) of all pages are included in order to facilitate tests with other OCR software.</abstract>
<identifier type="citekey">clematide-etal-2016-crowdsourcing</identifier>
<location>
<url>https://aclanthology.org/L16-1155</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>975</start>
<end>982</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Crowdsourcing an OCR Gold Standard for a German and French Heritage Corpus
%A Clematide, Simon
%A Furrer, Lenz
%A Volk, Martin
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F clematide-etal-2016-crowdsourcing
%X Crowdsourcing approaches for post-correction of OCR output (Optical Character Recognition) have been successfully applied to several historic text collections. We report on our crowd-correction platform Kokos, which we built to improve the OCR quality of the digitized yearbooks of the Swiss Alpine Club (SAC) from the 19th century. This multilingual heritage corpus consists of Alpine texts mainly written in German and French, all typeset in Antiqua font. Finding and engaging volunteers for correcting large amounts of pages into high quality text requires a carefully designed user interface, an easy-to-use workflow, and continuous efforts for keeping the participants motivated. More than 180,000 characters on about 21,000 pages were corrected by volunteers in about 7 month, achieving an OCR gold standard with a systematically evaluated accuracy of 99.7% on the word level. The crowdsourced OCR gold standard and the corresponding original OCR recognition results from Abby FineReader 7 for each page are available as a resource. Additionally, the scanned images (300dpi) of all pages are included in order to facilitate tests with other OCR software.
%U https://aclanthology.org/L16-1155
%P 975-982
Markdown (Informal)
[Crowdsourcing an OCR Gold Standard for a German and French Heritage Corpus](https://aclanthology.org/L16-1155) (Clematide et al., LREC 2016)
ACL