@inproceedings{booth-etal-2022-language,
title = "A Language Modelling Approach to Quality Assessment of {OCR}`ed Historical Text",
author = "Booth, Callum and
Shoemaker, Robert and
Gaizauskas, Robert",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.630/",
pages = "5859--5864",
abstract = "We hypothesise and evaluate a language model-based approach for scoring the quality of OCR transcriptions in the British Library Newspapers (BLN) corpus parts 1 and 2, to identify the best quality OCR for use in further natural language processing tasks, with a wider view to link individual newspaper reports of crime in nineteenth-century London to the Digital Panopticon{---}a structured repository of criminal lives. We mitigate the absence of gold standard transcriptions of the BLN corpus by utilising a corpus of genre-adjacent texts that capture the common and legal parlance of nineteenth-century London{---}the Proceedings of the Old Bailey Online{---}with a view to rank the BLN transcriptions by their OCR quality."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="booth-etal-2022-language">
<titleInfo>
<title>A Language Modelling Approach to Quality Assessment of OCR‘ed Historical Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Callum</namePart>
<namePart type="family">Booth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Shoemaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Gaizauskas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>We hypothesise and evaluate a language model-based approach for scoring the quality of OCR transcriptions in the British Library Newspapers (BLN) corpus parts 1 and 2, to identify the best quality OCR for use in further natural language processing tasks, with a wider view to link individual newspaper reports of crime in nineteenth-century London to the Digital Panopticon—a structured repository of criminal lives. We mitigate the absence of gold standard transcriptions of the BLN corpus by utilising a corpus of genre-adjacent texts that capture the common and legal parlance of nineteenth-century London—the Proceedings of the Old Bailey Online—with a view to rank the BLN transcriptions by their OCR quality.</abstract>
<identifier type="citekey">booth-etal-2022-language</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.630/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5859</start>
<end>5864</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Language Modelling Approach to Quality Assessment of OCR‘ed Historical Text
%A Booth, Callum
%A Shoemaker, Robert
%A Gaizauskas, Robert
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F booth-etal-2022-language
%X We hypothesise and evaluate a language model-based approach for scoring the quality of OCR transcriptions in the British Library Newspapers (BLN) corpus parts 1 and 2, to identify the best quality OCR for use in further natural language processing tasks, with a wider view to link individual newspaper reports of crime in nineteenth-century London to the Digital Panopticon—a structured repository of criminal lives. We mitigate the absence of gold standard transcriptions of the BLN corpus by utilising a corpus of genre-adjacent texts that capture the common and legal parlance of nineteenth-century London—the Proceedings of the Old Bailey Online—with a view to rank the BLN transcriptions by their OCR quality.
%U https://aclanthology.org/2022.lrec-1.630/
%P 5859-5864
Markdown (Informal)
[A Language Modelling Approach to Quality Assessment of OCR’ed Historical Text](https://aclanthology.org/2022.lrec-1.630/) (Booth et al., LREC 2022)
ACL