@inproceedings{afli-etal-2016-using,
title = "Using {SMT} for {OCR} Error Correction of Historical Texts",
author = "Afli, Haithem and
Qiu, Zhengwei and
Way, Andy and
Sheridan, P{\'a}raic",
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/L16-1153",
pages = "962--966",
abstract = "A trend to digitize historical paper-based archives has emerged in recent years, with the advent of digital optical scanners. A lot of paper-based books, textbooks, magazines, articles, and documents are being transformed into electronic versions that can be manipulated by a computer. For this purpose, Optical Character Recognition (OCR) systems have been developed to transform scanned digital text into editable computer text. However, different kinds of errors in the OCR system output text can be found, but Automatic Error Correction tools can help in performing the quality of electronic texts by cleaning and removing noises. In this paper, we perform a qualitative and quantitative comparison of several error-correction techniques for historical French documents. Experimentation shows that our Machine Translation for Error Correction method is superior to other Language Modelling correction techniques, with nearly 13{\%} relative improvement compared to the initial baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="afli-etal-2016-using">
<titleInfo>
<title>Using SMT for OCR Error Correction of Historical Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haithem</namePart>
<namePart type="family">Afli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengwei</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Way</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Páraic</namePart>
<namePart type="family">Sheridan</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>A trend to digitize historical paper-based archives has emerged in recent years, with the advent of digital optical scanners. A lot of paper-based books, textbooks, magazines, articles, and documents are being transformed into electronic versions that can be manipulated by a computer. For this purpose, Optical Character Recognition (OCR) systems have been developed to transform scanned digital text into editable computer text. However, different kinds of errors in the OCR system output text can be found, but Automatic Error Correction tools can help in performing the quality of electronic texts by cleaning and removing noises. In this paper, we perform a qualitative and quantitative comparison of several error-correction techniques for historical French documents. Experimentation shows that our Machine Translation for Error Correction method is superior to other Language Modelling correction techniques, with nearly 13% relative improvement compared to the initial baseline.</abstract>
<identifier type="citekey">afli-etal-2016-using</identifier>
<location>
<url>https://aclanthology.org/L16-1153</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>962</start>
<end>966</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using SMT for OCR Error Correction of Historical Texts
%A Afli, Haithem
%A Qiu, Zhengwei
%A Way, Andy
%A Sheridan, Páraic
%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 afli-etal-2016-using
%X A trend to digitize historical paper-based archives has emerged in recent years, with the advent of digital optical scanners. A lot of paper-based books, textbooks, magazines, articles, and documents are being transformed into electronic versions that can be manipulated by a computer. For this purpose, Optical Character Recognition (OCR) systems have been developed to transform scanned digital text into editable computer text. However, different kinds of errors in the OCR system output text can be found, but Automatic Error Correction tools can help in performing the quality of electronic texts by cleaning and removing noises. In this paper, we perform a qualitative and quantitative comparison of several error-correction techniques for historical French documents. Experimentation shows that our Machine Translation for Error Correction method is superior to other Language Modelling correction techniques, with nearly 13% relative improvement compared to the initial baseline.
%U https://aclanthology.org/L16-1153
%P 962-966
Markdown (Informal)
[Using SMT for OCR Error Correction of Historical Texts](https://aclanthology.org/L16-1153) (Afli et al., LREC 2016)
ACL
- Haithem Afli, Zhengwei Qiu, Andy Way, and Páraic Sheridan. 2016. Using SMT for OCR Error Correction of Historical Texts. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 962–966, Portorož, Slovenia. European Language Resources Association (ELRA).