@inproceedings{poncelas-etal-2020-tool,
title = "A Tool for Facilitating {OCR} Postediting in Historical Documents",
author = "Poncelas, Alberto and
Aboomar, Mohammad and
Buts, Jan and
Hadley, James and
Way, Andy",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2020.lt4hala-1.7/",
pages = "47--51",
language = "eng",
ISBN = "979-10-95546-53-5",
abstract = "Optical character recognition (OCR) for historical documents is a complex procedure subject to a unique set of material issues, including inconsistencies in typefaces and low quality scanning. Consequently, even the most sophisticated OCR engines produce errors. This paper reports on a tool built for postediting the output of Tesseract, more specifically for correcting common errors in digitized historical documents. The proposed tool suggests alternatives for word forms not found in a specified vocabulary. The assumed error is replaced by a presumably correct alternative in the post-edition based on the scores of a Language Model (LM). The tool is tested on a chapter of the book An Essay Towards Regulating the Trade and Employing the Poor of this Kingdom (Cary, 1719). As demonstrated below, the tool is successful in correcting a number of common errors. If sometimes unreliable, it is also transparent and subject to human intervention."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poncelas-etal-2020-tool">
<titleInfo>
<title>A Tool for Facilitating OCR Postediting in Historical Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Poncelas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Aboomar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Buts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Hadley</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>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-53-5</identifier>
</relatedItem>
<abstract>Optical character recognition (OCR) for historical documents is a complex procedure subject to a unique set of material issues, including inconsistencies in typefaces and low quality scanning. Consequently, even the most sophisticated OCR engines produce errors. This paper reports on a tool built for postediting the output of Tesseract, more specifically for correcting common errors in digitized historical documents. The proposed tool suggests alternatives for word forms not found in a specified vocabulary. The assumed error is replaced by a presumably correct alternative in the post-edition based on the scores of a Language Model (LM). The tool is tested on a chapter of the book An Essay Towards Regulating the Trade and Employing the Poor of this Kingdom (Cary, 1719). As demonstrated below, the tool is successful in correcting a number of common errors. If sometimes unreliable, it is also transparent and subject to human intervention.</abstract>
<identifier type="citekey">poncelas-etal-2020-tool</identifier>
<location>
<url>https://aclanthology.org/2020.lt4hala-1.7/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>47</start>
<end>51</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Tool for Facilitating OCR Postediting in Historical Documents
%A Poncelas, Alberto
%A Aboomar, Mohammad
%A Buts, Jan
%A Hadley, James
%A Way, Andy
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages
%D 2020
%8 May
%I European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-53-5
%G eng
%F poncelas-etal-2020-tool
%X Optical character recognition (OCR) for historical documents is a complex procedure subject to a unique set of material issues, including inconsistencies in typefaces and low quality scanning. Consequently, even the most sophisticated OCR engines produce errors. This paper reports on a tool built for postediting the output of Tesseract, more specifically for correcting common errors in digitized historical documents. The proposed tool suggests alternatives for word forms not found in a specified vocabulary. The assumed error is replaced by a presumably correct alternative in the post-edition based on the scores of a Language Model (LM). The tool is tested on a chapter of the book An Essay Towards Regulating the Trade and Employing the Poor of this Kingdom (Cary, 1719). As demonstrated below, the tool is successful in correcting a number of common errors. If sometimes unreliable, it is also transparent and subject to human intervention.
%U https://aclanthology.org/2020.lt4hala-1.7/
%P 47-51
Markdown (Informal)
[A Tool for Facilitating OCR Postediting in Historical Documents](https://aclanthology.org/2020.lt4hala-1.7/) (Poncelas et al., LT4HALA 2020)
ACL
- Alberto Poncelas, Mohammad Aboomar, Jan Buts, James Hadley, and Andy Way. 2020. A Tool for Facilitating OCR Postediting in Historical Documents. In Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages, pages 47–51, Marseille, France. European Language Resources Association (ELRA).