@inproceedings{isaacs-etal-2024-humanitarian-corpora,
title = "Humanitarian Corpora for {E}nglish, {F}rench and {S}panish",
author = "Isaacs, Loryn and
Chamb{\'o}, Santiago and
Le{\'o}n-Ara{\'u}z, Pilar",
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.738",
pages = "8418--8426",
abstract = "This paper presents three corpora of English, French and Spanish humanitarian documents compiled with reports obtained from ReliefWeb through its API. ReliefWeb is a leading database of humanitarian documents operated by the UN Office for the Coordination of Humanitarian Affairs (OCHA). To compile these corpora, documents were selected with language identification and noise reduction techniques. They were subsequently tokenized, lemmatized, tagged by part of speech, and enriched with metadata for use by linguists in corpus query software. These corpora were compiled to satisfy the research needs of the Humanitarian Encyclopedia, a project with a focus on conceptual variation. However, they can also be useful for other humanitarian endeavors, whether they are research- or practitioner-oriented; the source code for generating the corpora is available on GitHub. To compare materials, an exploratory analysis of definitional and generic-specific information was conducted for the concept of ARMED ACTOR with lexical data extracted from an English legacy corpus (where the concept is underrepresented) as well as on the new English and Spanish corpora. Lexical data were compared among corpora and presented by means of online data visualization to illustrate its potential to inform conceptual modelling.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="isaacs-etal-2024-humanitarian-corpora">
<titleInfo>
<title>Humanitarian Corpora for English, French and Spanish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loryn</namePart>
<namePart type="family">Isaacs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Chambó</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pilar</namePart>
<namePart type="family">León-Araúz</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>This paper presents three corpora of English, French and Spanish humanitarian documents compiled with reports obtained from ReliefWeb through its API. ReliefWeb is a leading database of humanitarian documents operated by the UN Office for the Coordination of Humanitarian Affairs (OCHA). To compile these corpora, documents were selected with language identification and noise reduction techniques. They were subsequently tokenized, lemmatized, tagged by part of speech, and enriched with metadata for use by linguists in corpus query software. These corpora were compiled to satisfy the research needs of the Humanitarian Encyclopedia, a project with a focus on conceptual variation. However, they can also be useful for other humanitarian endeavors, whether they are research- or practitioner-oriented; the source code for generating the corpora is available on GitHub. To compare materials, an exploratory analysis of definitional and generic-specific information was conducted for the concept of ARMED ACTOR with lexical data extracted from an English legacy corpus (where the concept is underrepresented) as well as on the new English and Spanish corpora. Lexical data were compared among corpora and presented by means of online data visualization to illustrate its potential to inform conceptual modelling.</abstract>
<identifier type="citekey">isaacs-etal-2024-humanitarian-corpora</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.738</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>8418</start>
<end>8426</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Humanitarian Corpora for English, French and Spanish
%A Isaacs, Loryn
%A Chambó, Santiago
%A León-Araúz, Pilar
%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 isaacs-etal-2024-humanitarian-corpora
%X This paper presents three corpora of English, French and Spanish humanitarian documents compiled with reports obtained from ReliefWeb through its API. ReliefWeb is a leading database of humanitarian documents operated by the UN Office for the Coordination of Humanitarian Affairs (OCHA). To compile these corpora, documents were selected with language identification and noise reduction techniques. They were subsequently tokenized, lemmatized, tagged by part of speech, and enriched with metadata for use by linguists in corpus query software. These corpora were compiled to satisfy the research needs of the Humanitarian Encyclopedia, a project with a focus on conceptual variation. However, they can also be useful for other humanitarian endeavors, whether they are research- or practitioner-oriented; the source code for generating the corpora is available on GitHub. To compare materials, an exploratory analysis of definitional and generic-specific information was conducted for the concept of ARMED ACTOR with lexical data extracted from an English legacy corpus (where the concept is underrepresented) as well as on the new English and Spanish corpora. Lexical data were compared among corpora and presented by means of online data visualization to illustrate its potential to inform conceptual modelling.
%U https://aclanthology.org/2024.lrec-main.738
%P 8418-8426
Markdown (Informal)
[Humanitarian Corpora for English, French and Spanish](https://aclanthology.org/2024.lrec-main.738) (Isaacs et al., LREC-COLING 2024)
ACL
- Loryn Isaacs, Santiago Chambó, and Pilar León-Araúz. 2024. Humanitarian Corpora for English, French and Spanish. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 8418–8426, Torino, Italia. ELRA and ICCL.