@inproceedings{booth-etal-2024-bln600,
title = "{BLN}600: A Parallel Corpus of Machine/Human Transcribed Nineteenth Century Newspaper Texts",
author = "Booth, Callum William and
Thomas, Alan and
Gaizauskas, Robert",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.219",
pages = "2440--2446",
abstract = "We present a publicly available corpus of nineteenth-century newspaper text focused on crime in London, derived from the Gale British Library Newspapers corpus parts 1 and 2. The corpus comprises 600 newspaper excerpts and for each excerpt contains the original source image, the machine transcription of that image as found in the BLN and a gold standard manual transcription that we have created. We envisage the corpus will be helpful for the training and development of OCR and post-OCR correction methodologies for historical newspaper machine transcription{---}for which there is currently a dearth of publicly available resources. In this paper, we discuss the rationale behind gathering such a corpus, the methodology used to select, process, and align the data, and the corpus{'} potential utility for historians and digital humanities researchers{---}particularly within the realms of neural machine translation-based post-OCR correction approaches, and other natural language processing tasks that are critically affected by erroneous OCR.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="booth-etal-2024-bln600">
<titleInfo>
<title>BLN600: A Parallel Corpus of Machine/Human Transcribed Nineteenth Century Newspaper Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Callum</namePart>
<namePart type="given">William</namePart>
<namePart type="family">Booth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Thomas</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>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a publicly available corpus of nineteenth-century newspaper text focused on crime in London, derived from the Gale British Library Newspapers corpus parts 1 and 2. The corpus comprises 600 newspaper excerpts and for each excerpt contains the original source image, the machine transcription of that image as found in the BLN and a gold standard manual transcription that we have created. We envisage the corpus will be helpful for the training and development of OCR and post-OCR correction methodologies for historical newspaper machine transcription—for which there is currently a dearth of publicly available resources. In this paper, we discuss the rationale behind gathering such a corpus, the methodology used to select, process, and align the data, and the corpus’ potential utility for historians and digital humanities researchers—particularly within the realms of neural machine translation-based post-OCR correction approaches, and other natural language processing tasks that are critically affected by erroneous OCR.</abstract>
<identifier type="citekey">booth-etal-2024-bln600</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.219</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2440</start>
<end>2446</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BLN600: A Parallel Corpus of Machine/Human Transcribed Nineteenth Century Newspaper Texts
%A Booth, Callum William
%A Thomas, Alan
%A Gaizauskas, Robert
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F booth-etal-2024-bln600
%X We present a publicly available corpus of nineteenth-century newspaper text focused on crime in London, derived from the Gale British Library Newspapers corpus parts 1 and 2. The corpus comprises 600 newspaper excerpts and for each excerpt contains the original source image, the machine transcription of that image as found in the BLN and a gold standard manual transcription that we have created. We envisage the corpus will be helpful for the training and development of OCR and post-OCR correction methodologies for historical newspaper machine transcription—for which there is currently a dearth of publicly available resources. In this paper, we discuss the rationale behind gathering such a corpus, the methodology used to select, process, and align the data, and the corpus’ potential utility for historians and digital humanities researchers—particularly within the realms of neural machine translation-based post-OCR correction approaches, and other natural language processing tasks that are critically affected by erroneous OCR.
%U https://aclanthology.org/2024.lrec-main.219
%P 2440-2446
Markdown (Informal)
[BLN600: A Parallel Corpus of Machine/Human Transcribed Nineteenth Century Newspaper Texts](https://aclanthology.org/2024.lrec-main.219) (Booth et al., LREC-COLING 2024)
ACL
