@inproceedings{wiriyathammabhum-2022-classbases,
title = "{C}lass{B}ases at the {CASE}-2022 Multilingual Protest Event Detection Task: Multilingual Protest News Detection and Automatically Replicating Manually Created Event Datasets",
author = "Wiriyathammabhum, Peratham",
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-1.21",
doi = "10.18653/v1/2022.case-1.21",
pages = "149--154",
abstract = "In this report, we describe our ClassBases submissions to a shared task on multilingual protest event detection. For the multilingual protest news detection, we participated in subtask-1, subtask-2 and subtask-4 which are document classification, sentence classification and token classification. In subtask-1, we compare XLM-RoBERTa-base, mLUKE-base and XLM-RoBERTa-large on finetuning in a sequential classification setting. We always use a combination of the training data from every language provided to train our multilingual models. We found that larger models seem to work better and entity knowledge helps but at a non-negligible cost. For subtask-2, we only submitted an mLUKE-base system for sentence classification. For subtask-4, we only submitted an XLM-RoBERTa-base for token classification system for sequence labeling. For automatically replicating manually created event datasets, we participated in COVID-related protest events from the New York Times news corpus. We created a system to process the crawled data into a dataset of protest events.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wiriyathammabhum-2022-classbases">
<titleInfo>
<title>ClassBases at the CASE-2022 Multilingual Protest Event Detection Task: Multilingual Protest News Detection and Automatically Replicating Manually Created Event Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peratham</namePart>
<namePart type="family">Wiriyathammabhum</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>In this report, we describe our ClassBases submissions to a shared task on multilingual protest event detection. For the multilingual protest news detection, we participated in subtask-1, subtask-2 and subtask-4 which are document classification, sentence classification and token classification. In subtask-1, we compare XLM-RoBERTa-base, mLUKE-base and XLM-RoBERTa-large on finetuning in a sequential classification setting. We always use a combination of the training data from every language provided to train our multilingual models. We found that larger models seem to work better and entity knowledge helps but at a non-negligible cost. For subtask-2, we only submitted an mLUKE-base system for sentence classification. For subtask-4, we only submitted an XLM-RoBERTa-base for token classification system for sequence labeling. For automatically replicating manually created event datasets, we participated in COVID-related protest events from the New York Times news corpus. We created a system to process the crawled data into a dataset of protest events.</abstract>
<identifier type="citekey">wiriyathammabhum-2022-classbases</identifier>
<identifier type="doi">10.18653/v1/2022.case-1.21</identifier>
<location>
<url>https://aclanthology.org/2022.case-1.21</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>149</start>
<end>154</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ClassBases at the CASE-2022 Multilingual Protest Event Detection Task: Multilingual Protest News Detection and Automatically Replicating Manually Created Event Datasets
%A Wiriyathammabhum, Peratham
%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 wiriyathammabhum-2022-classbases
%X In this report, we describe our ClassBases submissions to a shared task on multilingual protest event detection. For the multilingual protest news detection, we participated in subtask-1, subtask-2 and subtask-4 which are document classification, sentence classification and token classification. In subtask-1, we compare XLM-RoBERTa-base, mLUKE-base and XLM-RoBERTa-large on finetuning in a sequential classification setting. We always use a combination of the training data from every language provided to train our multilingual models. We found that larger models seem to work better and entity knowledge helps but at a non-negligible cost. For subtask-2, we only submitted an mLUKE-base system for sentence classification. For subtask-4, we only submitted an XLM-RoBERTa-base for token classification system for sequence labeling. For automatically replicating manually created event datasets, we participated in COVID-related protest events from the New York Times news corpus. We created a system to process the crawled data into a dataset of protest events.
%R 10.18653/v1/2022.case-1.21
%U https://aclanthology.org/2022.case-1.21
%U https://doi.org/10.18653/v1/2022.case-1.21
%P 149-154
Markdown (Informal)
[ClassBases at the CASE-2022 Multilingual Protest Event Detection Task: Multilingual Protest News Detection and Automatically Replicating Manually Created Event Datasets](https://aclanthology.org/2022.case-1.21) (Wiriyathammabhum, CASE 2022)
ACL