@inproceedings{dementieva-etal-2024-toxicity,
title = "Toxicity Classification in {U}krainian",
author = "Dementieva, Daryna and
Khylenko, Valeriia and
Babakov, Nikolay and
Groh, Georg",
editor = {Chung, Yi-Ling and
Talat, Zeerak and
Nozza, Debora and
Plaza-del-Arco, Flor Miriam and
R{\"o}ttger, Paul and
Mostafazadeh Davani, Aida and
Calabrese, Agostina},
booktitle = "Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.woah-1.19",
doi = "10.18653/v1/2024.woah-1.19",
pages = "244--255",
abstract = "The task of toxicity detection is still a relevant task, especially in the context of safe and fair LMs development. Nevertheless, labeled binary toxicity classification corpora are not available for all languages, which is understandable given the resource-intensive nature of the annotation process. Ukrainian, in particular, is among the languages lacking such resources. To our knowledge, there has been no existing toxicity classification corpus in Ukrainian. In this study, we aim to fill this gap by investigating cross-lingual knowledge transfer techniques and creating labeled corpora by: (i){\textasciitilde}translating from an English corpus, (ii){\textasciitilde}filtering toxic samples using keywords, and (iii){\textasciitilde}annotating with crowdsourcing. We compare LLMs prompting and other cross-lingual transfer approaches with and without fine-tuning offering insights into the most robust and efficient baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dementieva-etal-2024-toxicity">
<titleInfo>
<title>Toxicity Classification in Ukrainian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daryna</namePart>
<namePart type="family">Dementieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valeriia</namePart>
<namePart type="family">Khylenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolay</namePart>
<namePart type="family">Babakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Groh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi-Ling</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Talat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flor</namePart>
<namePart type="given">Miriam</namePart>
<namePart type="family">Plaza-del-Arco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Röttger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Mostafazadeh Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agostina</namePart>
<namePart type="family">Calabrese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of toxicity detection is still a relevant task, especially in the context of safe and fair LMs development. Nevertheless, labeled binary toxicity classification corpora are not available for all languages, which is understandable given the resource-intensive nature of the annotation process. Ukrainian, in particular, is among the languages lacking such resources. To our knowledge, there has been no existing toxicity classification corpus in Ukrainian. In this study, we aim to fill this gap by investigating cross-lingual knowledge transfer techniques and creating labeled corpora by: (i)~translating from an English corpus, (ii)~filtering toxic samples using keywords, and (iii)~annotating with crowdsourcing. We compare LLMs prompting and other cross-lingual transfer approaches with and without fine-tuning offering insights into the most robust and efficient baselines.</abstract>
<identifier type="citekey">dementieva-etal-2024-toxicity</identifier>
<identifier type="doi">10.18653/v1/2024.woah-1.19</identifier>
<location>
<url>https://aclanthology.org/2024.woah-1.19</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>244</start>
<end>255</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Toxicity Classification in Ukrainian
%A Dementieva, Daryna
%A Khylenko, Valeriia
%A Babakov, Nikolay
%A Groh, Georg
%Y Chung, Yi-Ling
%Y Talat, Zeerak
%Y Nozza, Debora
%Y Plaza-del-Arco, Flor Miriam
%Y Röttger, Paul
%Y Mostafazadeh Davani, Aida
%Y Calabrese, Agostina
%S Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F dementieva-etal-2024-toxicity
%X The task of toxicity detection is still a relevant task, especially in the context of safe and fair LMs development. Nevertheless, labeled binary toxicity classification corpora are not available for all languages, which is understandable given the resource-intensive nature of the annotation process. Ukrainian, in particular, is among the languages lacking such resources. To our knowledge, there has been no existing toxicity classification corpus in Ukrainian. In this study, we aim to fill this gap by investigating cross-lingual knowledge transfer techniques and creating labeled corpora by: (i)~translating from an English corpus, (ii)~filtering toxic samples using keywords, and (iii)~annotating with crowdsourcing. We compare LLMs prompting and other cross-lingual transfer approaches with and without fine-tuning offering insights into the most robust and efficient baselines.
%R 10.18653/v1/2024.woah-1.19
%U https://aclanthology.org/2024.woah-1.19
%U https://doi.org/10.18653/v1/2024.woah-1.19
%P 244-255
Markdown (Informal)
[Toxicity Classification in Ukrainian](https://aclanthology.org/2024.woah-1.19) (Dementieva et al., WOAH-WS 2024)
ACL
- Daryna Dementieva, Valeriia Khylenko, Nikolay Babakov, and Georg Groh. 2024. Toxicity Classification in Ukrainian. In Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024), pages 244–255, Mexico City, Mexico. Association for Computational Linguistics.