@inproceedings{dobranic-etal-2024-lightweight,
title = "A Lightweight Approach to a Giga-Corpus of Historical Periodicals: The Story of a {S}lovenian Historical Newspaper Collection",
author = "Dobrani{\'c}, Filip and
Evkoski, Bojan and
Ljube{\v{s}}i{\'c}, Nikola",
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.61",
pages = "695--703",
abstract = "Preparing historical newspaper collections is a complicated endeavour, consisting of multiple steps that have to be carefully adapted to the specific content in question, including imaging, layout prediction, optical character recognition, and linguistic annotation. To address the high costs associated with the process, we present a lightweight approach to producing high-quality corpora and apply it to a massive collection of Slovenian historical newspapers from the 18th, 19th and 20th century resulting in a billion-word giga-corpus. We start with noisy OCR-ed data produced by different technologies in varying periods by the National and University Library of Slovenia. To address the inherent variability in the quality of textual data, a challenge commonly encountered in digital libraries globally, we perform a targeted post-digitisation correction procedure, coupled with a robust curation mechanism for noisy texts via language model inference. Subsequently, we subject the corrected and filtered output to comprehensive linguistic annotation, enriching the corpus with part-of-speech tags, lemmas, and named entity labels. Finally, we perform an analysis through topic modeling at the noun lemma level, along with a frequency analysis of the named entities, to confirm the viability of our corpus preparation method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dobranic-etal-2024-lightweight">
<titleInfo>
<title>A Lightweight Approach to a Giga-Corpus of Historical Periodicals: The Story of a Slovenian Historical Newspaper Collection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Dobranić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bojan</namePart>
<namePart type="family">Evkoski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</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>Preparing historical newspaper collections is a complicated endeavour, consisting of multiple steps that have to be carefully adapted to the specific content in question, including imaging, layout prediction, optical character recognition, and linguistic annotation. To address the high costs associated with the process, we present a lightweight approach to producing high-quality corpora and apply it to a massive collection of Slovenian historical newspapers from the 18th, 19th and 20th century resulting in a billion-word giga-corpus. We start with noisy OCR-ed data produced by different technologies in varying periods by the National and University Library of Slovenia. To address the inherent variability in the quality of textual data, a challenge commonly encountered in digital libraries globally, we perform a targeted post-digitisation correction procedure, coupled with a robust curation mechanism for noisy texts via language model inference. Subsequently, we subject the corrected and filtered output to comprehensive linguistic annotation, enriching the corpus with part-of-speech tags, lemmas, and named entity labels. Finally, we perform an analysis through topic modeling at the noun lemma level, along with a frequency analysis of the named entities, to confirm the viability of our corpus preparation method.</abstract>
<identifier type="citekey">dobranic-etal-2024-lightweight</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.61</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>695</start>
<end>703</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Lightweight Approach to a Giga-Corpus of Historical Periodicals: The Story of a Slovenian Historical Newspaper Collection
%A Dobranić, Filip
%A Evkoski, Bojan
%A Ljubešić, Nikola
%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 dobranic-etal-2024-lightweight
%X Preparing historical newspaper collections is a complicated endeavour, consisting of multiple steps that have to be carefully adapted to the specific content in question, including imaging, layout prediction, optical character recognition, and linguistic annotation. To address the high costs associated with the process, we present a lightweight approach to producing high-quality corpora and apply it to a massive collection of Slovenian historical newspapers from the 18th, 19th and 20th century resulting in a billion-word giga-corpus. We start with noisy OCR-ed data produced by different technologies in varying periods by the National and University Library of Slovenia. To address the inherent variability in the quality of textual data, a challenge commonly encountered in digital libraries globally, we perform a targeted post-digitisation correction procedure, coupled with a robust curation mechanism for noisy texts via language model inference. Subsequently, we subject the corrected and filtered output to comprehensive linguistic annotation, enriching the corpus with part-of-speech tags, lemmas, and named entity labels. Finally, we perform an analysis through topic modeling at the noun lemma level, along with a frequency analysis of the named entities, to confirm the viability of our corpus preparation method.
%U https://aclanthology.org/2024.lrec-main.61
%P 695-703
Markdown (Informal)
[A Lightweight Approach to a Giga-Corpus of Historical Periodicals: The Story of a Slovenian Historical Newspaper Collection](https://aclanthology.org/2024.lrec-main.61) (Dobranić et al., LREC-COLING 2024)
ACL