@inproceedings{rodier-carter-2020-online,
title = "Online Near-Duplicate Detection of News Articles",
author = "Rodier, Simon and
Carter, Dave",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.156",
pages = "1242--1249",
abstract = "Near-duplicate documents are particularly common in news media corpora. Editors often update wirefeed articles to address space constraints in print editions or to add local context; journalists often lightly modify previous articles with new information or minor corrections. Near-duplicate documents have potentially significant costs, including bloating corpora with redundant information (biasing techniques built upon such corpora) and requiring additional human and computational analytic resources for marginal benefit. Filtering near-duplicates out of a collection is thus important, and is particularly challenging in applications that require them to be filtered out in real-time with high precision. Previous near-duplicate detection methods typically work offline to identify all near-duplicate pairs in a set of documents. We propose an online system which flags a near-duplicate document by finding its most likely original. This system adapts the shingling algorithm proposed by Broder (1997), and we test it on a challenging dataset of web-based news articles. Our online system presents state-of-the-art F1-scores, and can be tuned to trade precision for recall and vice-versa. Given its performance and online nature, our method can be used in many real-world applications. We present one such application, filtering near-duplicates to improve productivity of human analysts in a situational awareness tool.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rodier-carter-2020-online">
<titleInfo>
<title>Online Near-Duplicate Detection of News Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Rodier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dave</namePart>
<namePart type="family">Carter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Near-duplicate documents are particularly common in news media corpora. Editors often update wirefeed articles to address space constraints in print editions or to add local context; journalists often lightly modify previous articles with new information or minor corrections. Near-duplicate documents have potentially significant costs, including bloating corpora with redundant information (biasing techniques built upon such corpora) and requiring additional human and computational analytic resources for marginal benefit. Filtering near-duplicates out of a collection is thus important, and is particularly challenging in applications that require them to be filtered out in real-time with high precision. Previous near-duplicate detection methods typically work offline to identify all near-duplicate pairs in a set of documents. We propose an online system which flags a near-duplicate document by finding its most likely original. This system adapts the shingling algorithm proposed by Broder (1997), and we test it on a challenging dataset of web-based news articles. Our online system presents state-of-the-art F1-scores, and can be tuned to trade precision for recall and vice-versa. Given its performance and online nature, our method can be used in many real-world applications. We present one such application, filtering near-duplicates to improve productivity of human analysts in a situational awareness tool.</abstract>
<identifier type="citekey">rodier-carter-2020-online</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.156</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1242</start>
<end>1249</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Online Near-Duplicate Detection of News Articles
%A Rodier, Simon
%A Carter, Dave
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F rodier-carter-2020-online
%X Near-duplicate documents are particularly common in news media corpora. Editors often update wirefeed articles to address space constraints in print editions or to add local context; journalists often lightly modify previous articles with new information or minor corrections. Near-duplicate documents have potentially significant costs, including bloating corpora with redundant information (biasing techniques built upon such corpora) and requiring additional human and computational analytic resources for marginal benefit. Filtering near-duplicates out of a collection is thus important, and is particularly challenging in applications that require them to be filtered out in real-time with high precision. Previous near-duplicate detection methods typically work offline to identify all near-duplicate pairs in a set of documents. We propose an online system which flags a near-duplicate document by finding its most likely original. This system adapts the shingling algorithm proposed by Broder (1997), and we test it on a challenging dataset of web-based news articles. Our online system presents state-of-the-art F1-scores, and can be tuned to trade precision for recall and vice-versa. Given its performance and online nature, our method can be used in many real-world applications. We present one such application, filtering near-duplicates to improve productivity of human analysts in a situational awareness tool.
%U https://aclanthology.org/2020.lrec-1.156
%P 1242-1249
Markdown (Informal)
[Online Near-Duplicate Detection of News Articles](https://aclanthology.org/2020.lrec-1.156) (Rodier & Carter, LREC 2020)
ACL