@inproceedings{alrashdi-okeefe-2022-domain,
title = "Domain Adaptation for {A}rabic Crisis Response",
author = "Alrashdi, Reem and
O{'}Keefe, Simon",
editor = "Bouamor, Houda and
Al-Khalifa, Hend and
Darwish, Kareem and
Rambow, Owen and
Bougares, Fethi and
Abdelali, Ahmed and
Tomeh, Nadi and
Khalifa, Salam and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.23",
doi = "10.18653/v1/2022.wanlp-1.23",
pages = "249--259",
abstract = "Deep learning algorithms can identify related tweets to reduce the information overload that prevents humanitarian organisations from using valuable Twitter posts. However, they rely heavily on human-labelled data, which are unavailable for emerging crises. Because each crisis has its own features, such as location, time and social media response, current models are known to suffer from generalising to unseen disaster events when pre-trained on past ones. Tweet classifiers for low-resource languages like Arabic has the additional issue of limited labelled data duplicates caused by the absence of good language resources. Thus, we propose a novel domain adaptation approach that employs distant supervision to automatically label tweets from emerging Arabic crisis events to be used to train a model along with available human-labelled data. We evaluate our work on data from seven 2018{--}2020 Arabic events from different crisis types (flood, explosion, virus and storm). Results show that our method outperforms self-training in identifying crisis-related tweets in real-time scenarios and can be seen as a robust Arabic tweet classifier.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alrashdi-okeefe-2022-domain">
<titleInfo>
<title>Domain Adaptation for Arabic Crisis Response</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reem</namePart>
<namePart type="family">Alrashdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">O’Keefe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Deep learning algorithms can identify related tweets to reduce the information overload that prevents humanitarian organisations from using valuable Twitter posts. However, they rely heavily on human-labelled data, which are unavailable for emerging crises. Because each crisis has its own features, such as location, time and social media response, current models are known to suffer from generalising to unseen disaster events when pre-trained on past ones. Tweet classifiers for low-resource languages like Arabic has the additional issue of limited labelled data duplicates caused by the absence of good language resources. Thus, we propose a novel domain adaptation approach that employs distant supervision to automatically label tweets from emerging Arabic crisis events to be used to train a model along with available human-labelled data. We evaluate our work on data from seven 2018–2020 Arabic events from different crisis types (flood, explosion, virus and storm). Results show that our method outperforms self-training in identifying crisis-related tweets in real-time scenarios and can be seen as a robust Arabic tweet classifier.</abstract>
<identifier type="citekey">alrashdi-okeefe-2022-domain</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.23</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.23</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>249</start>
<end>259</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain Adaptation for Arabic Crisis Response
%A Alrashdi, Reem
%A O’Keefe, Simon
%Y Bouamor, Houda
%Y Al-Khalifa, Hend
%Y Darwish, Kareem
%Y Rambow, Owen
%Y Bougares, Fethi
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Khalifa, Salam
%Y Zaghouani, Wajdi
%S Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F alrashdi-okeefe-2022-domain
%X Deep learning algorithms can identify related tweets to reduce the information overload that prevents humanitarian organisations from using valuable Twitter posts. However, they rely heavily on human-labelled data, which are unavailable for emerging crises. Because each crisis has its own features, such as location, time and social media response, current models are known to suffer from generalising to unseen disaster events when pre-trained on past ones. Tweet classifiers for low-resource languages like Arabic has the additional issue of limited labelled data duplicates caused by the absence of good language resources. Thus, we propose a novel domain adaptation approach that employs distant supervision to automatically label tweets from emerging Arabic crisis events to be used to train a model along with available human-labelled data. We evaluate our work on data from seven 2018–2020 Arabic events from different crisis types (flood, explosion, virus and storm). Results show that our method outperforms self-training in identifying crisis-related tweets in real-time scenarios and can be seen as a robust Arabic tweet classifier.
%R 10.18653/v1/2022.wanlp-1.23
%U https://aclanthology.org/2022.wanlp-1.23
%U https://doi.org/10.18653/v1/2022.wanlp-1.23
%P 249-259
Markdown (Informal)
[Domain Adaptation for Arabic Crisis Response](https://aclanthology.org/2022.wanlp-1.23) (Alrashdi & O’Keefe, WANLP 2022)
ACL
- Reem Alrashdi and Simon O’Keefe. 2022. Domain Adaptation for Arabic Crisis Response. In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), pages 249–259, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.