@inproceedings{lamba-etal-2024-humvi,
title = "{H}um{VI}: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid",
author = "Lamba, Hemank and
Abilov, Anton and
Zhang, Ke and
Olson, Elizabeth M and
Dambanemuya, Henry Kudzanai and
B{\'a}rcia, Jo{\~a}o Cordovil and
Batista, David S. and
Wille, Christina and
Cahill, Aoife and
Tetreault, Joel R. and
Jaimes, Alejandro",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.743/",
doi = "10.18653/v1/2024.findings-emnlp.743",
pages = "12705--12722",
abstract = "Humanitarian organizations can enhance their effectiveness by analyzing data to discover trends, gather aggregated insights, manage their security risks, support decision-making, and inform advocacy and funding proposals. However, data about violent incidents with direct impact and relevance for humanitarian aid operations is not readily available. An automatic data collection and NLP-backed classification framework aligned with humanitarian perspectives can help bridge this gap. In this paper, we present HumVI {--} a dataset comprising news articles in three languages (English, French, Arabic) containing instances of different types of violent incidents categorized by the humanitarian sector they impact, e.g., aid security, education, food security, health, and protection. Reliable labels were obtained for the dataset by partnering with a data-backed humanitarian organization, Insecurity Insight. We provide multiple benchmarks for the dataset, employing various deep learning architectures and techniques, including data augmentation and mask loss, to address different task-related challenges, e.g., domain expansion. The dataset is publicly available at https://github.com/dataminr-ai/humvi-dataset."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lamba-etal-2024-humvi">
<titleInfo>
<title>HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hemank</namePart>
<namePart type="family">Lamba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anton</namePart>
<namePart type="family">Abilov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Olson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henry</namePart>
<namePart type="given">Kudzanai</namePart>
<namePart type="family">Dambanemuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="given">Cordovil</namePart>
<namePart type="family">Bárcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Batista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christina</namePart>
<namePart type="family">Wille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aoife</namePart>
<namePart type="family">Cahill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alejandro</namePart>
<namePart type="family">Jaimes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Humanitarian organizations can enhance their effectiveness by analyzing data to discover trends, gather aggregated insights, manage their security risks, support decision-making, and inform advocacy and funding proposals. However, data about violent incidents with direct impact and relevance for humanitarian aid operations is not readily available. An automatic data collection and NLP-backed classification framework aligned with humanitarian perspectives can help bridge this gap. In this paper, we present HumVI – a dataset comprising news articles in three languages (English, French, Arabic) containing instances of different types of violent incidents categorized by the humanitarian sector they impact, e.g., aid security, education, food security, health, and protection. Reliable labels were obtained for the dataset by partnering with a data-backed humanitarian organization, Insecurity Insight. We provide multiple benchmarks for the dataset, employing various deep learning architectures and techniques, including data augmentation and mask loss, to address different task-related challenges, e.g., domain expansion. The dataset is publicly available at https://github.com/dataminr-ai/humvi-dataset.</abstract>
<identifier type="citekey">lamba-etal-2024-humvi</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.743</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.743/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>12705</start>
<end>12722</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid
%A Lamba, Hemank
%A Abilov, Anton
%A Zhang, Ke
%A Olson, Elizabeth M.
%A Dambanemuya, Henry Kudzanai
%A Bárcia, João Cordovil
%A Batista, David S.
%A Wille, Christina
%A Cahill, Aoife
%A Tetreault, Joel R.
%A Jaimes, Alejandro
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F lamba-etal-2024-humvi
%X Humanitarian organizations can enhance their effectiveness by analyzing data to discover trends, gather aggregated insights, manage their security risks, support decision-making, and inform advocacy and funding proposals. However, data about violent incidents with direct impact and relevance for humanitarian aid operations is not readily available. An automatic data collection and NLP-backed classification framework aligned with humanitarian perspectives can help bridge this gap. In this paper, we present HumVI – a dataset comprising news articles in three languages (English, French, Arabic) containing instances of different types of violent incidents categorized by the humanitarian sector they impact, e.g., aid security, education, food security, health, and protection. Reliable labels were obtained for the dataset by partnering with a data-backed humanitarian organization, Insecurity Insight. We provide multiple benchmarks for the dataset, employing various deep learning architectures and techniques, including data augmentation and mask loss, to address different task-related challenges, e.g., domain expansion. The dataset is publicly available at https://github.com/dataminr-ai/humvi-dataset.
%R 10.18653/v1/2024.findings-emnlp.743
%U https://aclanthology.org/2024.findings-emnlp.743/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.743
%P 12705-12722
Markdown (Informal)
[HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid](https://aclanthology.org/2024.findings-emnlp.743/) (Lamba et al., Findings 2024)
ACL
- Hemank Lamba, Anton Abilov, Ke Zhang, Elizabeth M Olson, Henry Kudzanai Dambanemuya, João Cordovil Bárcia, David S. Batista, Christina Wille, Aoife Cahill, Joel R. Tetreault, and Alejandro Jaimes. 2024. HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 12705–12722, Miami, Florida, USA. Association for Computational Linguistics.