@inproceedings{hurriyetoglu-etal-2022-extended,
title = "Extended Multilingual Protest News Detection - Shared Task 1, {CASE} 2021 and 2022",
author = {H{\"u}rriyeto{\u{g}}lu, Ali and
Mutlu, Osman and
Duru{\c{s}}an, F{\i}rat and
Uca, Onur and
G{\"u}rel, Alaeddin and
Radford, Benjamin J. and
Dai, Yaoyao and
Hettiarachchi, Hansi and
Stoehr, Niklas and
Nomoto, Tadashi and
Slavcheva, Milena and
Vargas, Francielle and
Javid, Aaqib and
Beyhan, Fatih and
Y{\"o}r{\"u}k, Erdem},
editor = {H{\"u}rriyeto{\u{g}}lu, Ali and
Tanev, Hristo and
Zavarella, Vanni and
Y{\"o}r{\"u}k, Erdem},
booktitle = "Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.case-1.31",
doi = "10.18653/v1/2022.case-1.31",
pages = "223--228",
abstract = "We report results of the CASE 2022 Shared Task 1 on Multilingual Protest Event Detection. This task is a continuation of CASE 2021 that consists of four subtasks that are i) document classification, ii) sentence classification, iii) event sentence coreference identification, and iv) event extraction. The CASE 2022 extension consists of expanding the test data with more data in previously available languages, namely, English, Hindi, Portuguese, and Spanish, and adding new test data in Mandarin, Turkish, and Urdu for Sub-task 1, document classification. The training data from CASE 2021 in English, Portuguese and Spanish were utilized. Therefore, predicting document labels in Hindi, Mandarin, Turkish, and Urdu occurs in a zero-shot setting. The CASE 2022 workshop accepts reports on systems developed for predicting test data of CASE 2021 as well. We observe that the best systems submitted by CASE 2022 participants achieve between 79.71 and 84.06 F1-macro for new languages in a zero-shot setting. The winning approaches are mainly ensembling models and merging data in multiple languages. The best two submissions on CASE 2021 data outperform submissions from last year for Subtask 1 and Subtask 2 in all languages. Only the following scenarios were not outperformed by new submissions on CASE 2021: Subtask 3 Portuguese {\&} Subtask 4 English.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hurriyetoglu-etal-2022-extended">
<titleInfo>
<title>Extended Multilingual Protest News Detection - Shared Task 1, CASE 2021 and 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hürriyetoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Osman</namePart>
<namePart type="family">Mutlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fırat</namePart>
<namePart type="family">Duruşan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Onur</namePart>
<namePart type="family">Uca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alaeddin</namePart>
<namePart type="family">Gürel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Radford</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaoyao</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niklas</namePart>
<namePart type="family">Stoehr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tadashi</namePart>
<namePart type="family">Nomoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milena</namePart>
<namePart type="family">Slavcheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francielle</namePart>
<namePart type="family">Vargas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaqib</namePart>
<namePart type="family">Javid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatih</namePart>
<namePart type="family">Beyhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erdem</namePart>
<namePart type="family">Yörük</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 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hürriyetoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hristo</namePart>
<namePart type="family">Tanev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vanni</namePart>
<namePart type="family">Zavarella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erdem</namePart>
<namePart type="family">Yörük</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>We report results of the CASE 2022 Shared Task 1 on Multilingual Protest Event Detection. This task is a continuation of CASE 2021 that consists of four subtasks that are i) document classification, ii) sentence classification, iii) event sentence coreference identification, and iv) event extraction. The CASE 2022 extension consists of expanding the test data with more data in previously available languages, namely, English, Hindi, Portuguese, and Spanish, and adding new test data in Mandarin, Turkish, and Urdu for Sub-task 1, document classification. The training data from CASE 2021 in English, Portuguese and Spanish were utilized. Therefore, predicting document labels in Hindi, Mandarin, Turkish, and Urdu occurs in a zero-shot setting. The CASE 2022 workshop accepts reports on systems developed for predicting test data of CASE 2021 as well. We observe that the best systems submitted by CASE 2022 participants achieve between 79.71 and 84.06 F1-macro for new languages in a zero-shot setting. The winning approaches are mainly ensembling models and merging data in multiple languages. The best two submissions on CASE 2021 data outperform submissions from last year for Subtask 1 and Subtask 2 in all languages. Only the following scenarios were not outperformed by new submissions on CASE 2021: Subtask 3 Portuguese & Subtask 4 English.</abstract>
<identifier type="citekey">hurriyetoglu-etal-2022-extended</identifier>
<identifier type="doi">10.18653/v1/2022.case-1.31</identifier>
<location>
<url>https://aclanthology.org/2022.case-1.31</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>223</start>
<end>228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extended Multilingual Protest News Detection - Shared Task 1, CASE 2021 and 2022
%A Hürriyetoğlu, Ali
%A Mutlu, Osman
%A Duruşan, Fırat
%A Uca, Onur
%A Gürel, Alaeddin
%A Radford, Benjamin J.
%A Dai, Yaoyao
%A Hettiarachchi, Hansi
%A Stoehr, Niklas
%A Nomoto, Tadashi
%A Slavcheva, Milena
%A Vargas, Francielle
%A Javid, Aaqib
%A Beyhan, Fatih
%A Yörük, Erdem
%Y Hürriyetoğlu, Ali
%Y Tanev, Hristo
%Y Zavarella, Vanni
%Y Yörük, Erdem
%S Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F hurriyetoglu-etal-2022-extended
%X We report results of the CASE 2022 Shared Task 1 on Multilingual Protest Event Detection. This task is a continuation of CASE 2021 that consists of four subtasks that are i) document classification, ii) sentence classification, iii) event sentence coreference identification, and iv) event extraction. The CASE 2022 extension consists of expanding the test data with more data in previously available languages, namely, English, Hindi, Portuguese, and Spanish, and adding new test data in Mandarin, Turkish, and Urdu for Sub-task 1, document classification. The training data from CASE 2021 in English, Portuguese and Spanish were utilized. Therefore, predicting document labels in Hindi, Mandarin, Turkish, and Urdu occurs in a zero-shot setting. The CASE 2022 workshop accepts reports on systems developed for predicting test data of CASE 2021 as well. We observe that the best systems submitted by CASE 2022 participants achieve between 79.71 and 84.06 F1-macro for new languages in a zero-shot setting. The winning approaches are mainly ensembling models and merging data in multiple languages. The best two submissions on CASE 2021 data outperform submissions from last year for Subtask 1 and Subtask 2 in all languages. Only the following scenarios were not outperformed by new submissions on CASE 2021: Subtask 3 Portuguese & Subtask 4 English.
%R 10.18653/v1/2022.case-1.31
%U https://aclanthology.org/2022.case-1.31
%U https://doi.org/10.18653/v1/2022.case-1.31
%P 223-228
Markdown (Informal)
[Extended Multilingual Protest News Detection - Shared Task 1, CASE 2021 and 2022](https://aclanthology.org/2022.case-1.31) (Hürriyetoğlu et al., CASE 2022)
ACL
- Ali Hürriyetoğlu, Osman Mutlu, Fırat Duruşan, Onur Uca, Alaeddin Gürel, Benjamin J. Radford, Yaoyao Dai, Hansi Hettiarachchi, Niklas Stoehr, Tadashi Nomoto, Milena Slavcheva, Francielle Vargas, Aaqib Javid, Fatih Beyhan, and Erdem Yörük. 2022. Extended Multilingual Protest News Detection - Shared Task 1, CASE 2021 and 2022. In Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE), pages 223–228, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.