@inproceedings{schone-etal-2014-corpus,
title = "Corpus and Evaluation of Handwriting Recognition of Historical Genealogical Records",
author = "Schone, Patrick and
Nielson, Heath and
Ward, Mark",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/253_Paper.pdf",
pages = "153--159",
abstract = "Over the last few decades, significant strides have been made in handwriting recognition (HR), which is the automatic transcription of handwritten documents. HR often focuses on modern handwritten material, but in the electronic age, the volume of handwritten material is rapidly declining. However, we believe HR is on the verge of having major application to historical record collections. In recent years, archives and genealogical organizations have conducted huge campaigns to transcribe valuable historical record content with such transcription being largely done through human-intensive labor. HR has the potential of revolutionizing these transcription endeavors. To test the hypothesis that this technology is close to applicability, and to provide a testbed for reducing any accuracy gaps, we have developed an evaluation paradigm for historical record handwriting recognition. We created a huge test corpus consisting of four historical data collections of four differing genres and three languages. In this paper, we provide the details of these extensive resources which we intend to release to the research community for further study. Since several research organizations have already participated in this evaluation, we also show initial results and comparisons to human levels of performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schone-etal-2014-corpus">
<titleInfo>
<title>Corpus and Evaluation of Handwriting Recognition of Historical Genealogical Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Schone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heath</namePart>
<namePart type="family">Nielson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Ward</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Over the last few decades, significant strides have been made in handwriting recognition (HR), which is the automatic transcription of handwritten documents. HR often focuses on modern handwritten material, but in the electronic age, the volume of handwritten material is rapidly declining. However, we believe HR is on the verge of having major application to historical record collections. In recent years, archives and genealogical organizations have conducted huge campaigns to transcribe valuable historical record content with such transcription being largely done through human-intensive labor. HR has the potential of revolutionizing these transcription endeavors. To test the hypothesis that this technology is close to applicability, and to provide a testbed for reducing any accuracy gaps, we have developed an evaluation paradigm for historical record handwriting recognition. We created a huge test corpus consisting of four historical data collections of four differing genres and three languages. In this paper, we provide the details of these extensive resources which we intend to release to the research community for further study. Since several research organizations have already participated in this evaluation, we also show initial results and comparisons to human levels of performance.</abstract>
<identifier type="citekey">schone-etal-2014-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/253_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>153</start>
<end>159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus and Evaluation of Handwriting Recognition of Historical Genealogical Records
%A Schone, Patrick
%A Nielson, Heath
%A Ward, Mark
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F schone-etal-2014-corpus
%X Over the last few decades, significant strides have been made in handwriting recognition (HR), which is the automatic transcription of handwritten documents. HR often focuses on modern handwritten material, but in the electronic age, the volume of handwritten material is rapidly declining. However, we believe HR is on the verge of having major application to historical record collections. In recent years, archives and genealogical organizations have conducted huge campaigns to transcribe valuable historical record content with such transcription being largely done through human-intensive labor. HR has the potential of revolutionizing these transcription endeavors. To test the hypothesis that this technology is close to applicability, and to provide a testbed for reducing any accuracy gaps, we have developed an evaluation paradigm for historical record handwriting recognition. We created a huge test corpus consisting of four historical data collections of four differing genres and three languages. In this paper, we provide the details of these extensive resources which we intend to release to the research community for further study. Since several research organizations have already participated in this evaluation, we also show initial results and comparisons to human levels of performance.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/253_Paper.pdf
%P 153-159
Markdown (Informal)
[Corpus and Evaluation of Handwriting Recognition of Historical Genealogical Records](http://www.lrec-conf.org/proceedings/lrec2014/pdf/253_Paper.pdf) (Schone et al., LREC 2014)
ACL