@inproceedings{mutuvi-etal-2020-dataset,
title = "A Dataset for Multi-lingual Epidemiological Event Extraction",
author = {Mutuvi, Stephen and
Doucet, Antoine and
Lejeune, Ga{\"e}l and
Odeo, Moses},
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-1.509",
pages = "4139--4144",
abstract = "This paper proposes a corpus for the development and evaluation of tools and techniques for identifying emerging infectious disease threats in online news text. The corpus can not only be used for information extraction, but also for other natural language processing (NLP) tasks such as text classification. We make use of articles published on the Program for Monitoring Emerging Diseases (ProMED) platform, which provides current information about outbreaks of infectious diseases globally. Among the key pieces of information present in the articles is the uniform resource locator (URL) to the online news sources where the outbreaks were originally reported. We detail the procedure followed to build the dataset, which includes leveraging the source URLs to retrieve the news reports and subsequently pre-processing the retrieved documents. We also report on experimental results of event extraction on the dataset using the Data Analysis for Information Extraction in any Language(DAnIEL) system. DAnIEL is a multilingual news surveillance system that leverages unique attributes associated with news reporting to extract events: repetition and saliency. The system has wide geographical and language coverage, including low-resource languages. In addition, we compare different classification approaches in terms of their ability to differentiate between epidemic-related and unrelated news articles that constitute the corpus.",
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="mutuvi-etal-2020-dataset">
<titleInfo>
<title>A Dataset for Multi-lingual Epidemiological Event Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Mutuvi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Doucet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaël</namePart>
<namePart type="family">Lejeune</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moses</namePart>
<namePart type="family">Odeo</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>This paper proposes a corpus for the development and evaluation of tools and techniques for identifying emerging infectious disease threats in online news text. The corpus can not only be used for information extraction, but also for other natural language processing (NLP) tasks such as text classification. We make use of articles published on the Program for Monitoring Emerging Diseases (ProMED) platform, which provides current information about outbreaks of infectious diseases globally. Among the key pieces of information present in the articles is the uniform resource locator (URL) to the online news sources where the outbreaks were originally reported. We detail the procedure followed to build the dataset, which includes leveraging the source URLs to retrieve the news reports and subsequently pre-processing the retrieved documents. We also report on experimental results of event extraction on the dataset using the Data Analysis for Information Extraction in any Language(DAnIEL) system. DAnIEL is a multilingual news surveillance system that leverages unique attributes associated with news reporting to extract events: repetition and saliency. The system has wide geographical and language coverage, including low-resource languages. In addition, we compare different classification approaches in terms of their ability to differentiate between epidemic-related and unrelated news articles that constitute the corpus.</abstract>
<identifier type="citekey">mutuvi-etal-2020-dataset</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.509</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4139</start>
<end>4144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dataset for Multi-lingual Epidemiological Event Extraction
%A Mutuvi, Stephen
%A Doucet, Antoine
%A Lejeune, Gaël
%A Odeo, Moses
%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 mutuvi-etal-2020-dataset
%X This paper proposes a corpus for the development and evaluation of tools and techniques for identifying emerging infectious disease threats in online news text. The corpus can not only be used for information extraction, but also for other natural language processing (NLP) tasks such as text classification. We make use of articles published on the Program for Monitoring Emerging Diseases (ProMED) platform, which provides current information about outbreaks of infectious diseases globally. Among the key pieces of information present in the articles is the uniform resource locator (URL) to the online news sources where the outbreaks were originally reported. We detail the procedure followed to build the dataset, which includes leveraging the source URLs to retrieve the news reports and subsequently pre-processing the retrieved documents. We also report on experimental results of event extraction on the dataset using the Data Analysis for Information Extraction in any Language(DAnIEL) system. DAnIEL is a multilingual news surveillance system that leverages unique attributes associated with news reporting to extract events: repetition and saliency. The system has wide geographical and language coverage, including low-resource languages. In addition, we compare different classification approaches in terms of their ability to differentiate between epidemic-related and unrelated news articles that constitute the corpus.
%U https://aclanthology.org/2020.lrec-1.509
%P 4139-4144
Markdown (Informal)
[A Dataset for Multi-lingual Epidemiological Event Extraction](https://aclanthology.org/2020.lrec-1.509) (Mutuvi et al., LREC 2020)
ACL