Cross-Cultural Transfer Learning for Chinese Offensive Language Detection

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Standard

Cross-Cultural Transfer Learning for Chinese Offensive Language Detection. / Zhou, Li; Cabello, Laura; Cao, Yong; Hershcovich, Daniel.

EACL 2023 - Cross-Cultural Considerations in NLP @ EACL, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2023. s. 8-15.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Harvard

Zhou, L, Cabello, L, Cao, Y & Hershcovich, D 2023, Cross-Cultural Transfer Learning for Chinese Offensive Language Detection. i EACL 2023 - Cross-Cultural Considerations in NLP @ EACL, Proceedings of the Workshop. Association for Computational Linguistics (ACL), s. 8-15, 1st Workshop on Cross-Cultural Considerations in NLP, C3NLP 2023, Dubrovnik, Kroatien, 05/05/2023. https://doi.org/10.18653/v1/2023.c3nlp-1.2

APA

Zhou, L., Cabello, L., Cao, Y., & Hershcovich, D. (2023). Cross-Cultural Transfer Learning for Chinese Offensive Language Detection. I EACL 2023 - Cross-Cultural Considerations in NLP @ EACL, Proceedings of the Workshop (s. 8-15). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2023.c3nlp-1.2

Vancouver

Zhou L, Cabello L, Cao Y, Hershcovich D. Cross-Cultural Transfer Learning for Chinese Offensive Language Detection. I EACL 2023 - Cross-Cultural Considerations in NLP @ EACL, Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2023. s. 8-15 https://doi.org/10.18653/v1/2023.c3nlp-1.2

Author

Zhou, Li ; Cabello, Laura ; Cao, Yong ; Hershcovich, Daniel. / Cross-Cultural Transfer Learning for Chinese Offensive Language Detection. EACL 2023 - Cross-Cultural Considerations in NLP @ EACL, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2023. s. 8-15

Bibtex

@inproceedings{acbd460d6a564e3187e1abad484ecb3e,
title = "Cross-Cultural Transfer Learning for Chinese Offensive Language Detection",
abstract = "Detecting offensive language is a challenging task. Generalizing across different cultures and languages becomes even more challenging: besides lexical, syntactic and semantic differences, pragmatic aspects such as cultural norms and sensitivities, which are particularly relevant in this context, vary greatly. In this paper, we target Chinese offensive language detection and aim to investigate the impact of transfer learning using offensive language detection data from different cultural backgrounds, specifically Korean and English. We find that culture-specific biases in what is considered offensive negatively impact the transferability of language models (LMs) and that LMs trained on diverse cultural data are sensitive to different features in Chinese offensive language detection. In a few-shot learning scenario, however, our study shows promising prospects for non-English offensive language detection with limited resources. Our findings highlight the importance of cross-cultural transfer learning in improving offensive language detection and promoting inclusive digital spaces.",
author = "Li Zhou and Laura Cabello and Yong Cao and Daniel Hershcovich",
note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 1st Workshop on Cross-Cultural Considerations in NLP, C3NLP 2023 ; Conference date: 05-05-2023",
year = "2023",
doi = "10.18653/v1/2023.c3nlp-1.2",
language = "English",
pages = "8--15",
booktitle = "EACL 2023 - Cross-Cultural Considerations in NLP @ EACL, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
address = "United States",

}

RIS

TY - GEN

T1 - Cross-Cultural Transfer Learning for Chinese Offensive Language Detection

AU - Zhou, Li

AU - Cabello, Laura

AU - Cao, Yong

AU - Hershcovich, Daniel

N1 - Publisher Copyright: © 2023 Association for Computational Linguistics.

PY - 2023

Y1 - 2023

N2 - Detecting offensive language is a challenging task. Generalizing across different cultures and languages becomes even more challenging: besides lexical, syntactic and semantic differences, pragmatic aspects such as cultural norms and sensitivities, which are particularly relevant in this context, vary greatly. In this paper, we target Chinese offensive language detection and aim to investigate the impact of transfer learning using offensive language detection data from different cultural backgrounds, specifically Korean and English. We find that culture-specific biases in what is considered offensive negatively impact the transferability of language models (LMs) and that LMs trained on diverse cultural data are sensitive to different features in Chinese offensive language detection. In a few-shot learning scenario, however, our study shows promising prospects for non-English offensive language detection with limited resources. Our findings highlight the importance of cross-cultural transfer learning in improving offensive language detection and promoting inclusive digital spaces.

AB - Detecting offensive language is a challenging task. Generalizing across different cultures and languages becomes even more challenging: besides lexical, syntactic and semantic differences, pragmatic aspects such as cultural norms and sensitivities, which are particularly relevant in this context, vary greatly. In this paper, we target Chinese offensive language detection and aim to investigate the impact of transfer learning using offensive language detection data from different cultural backgrounds, specifically Korean and English. We find that culture-specific biases in what is considered offensive negatively impact the transferability of language models (LMs) and that LMs trained on diverse cultural data are sensitive to different features in Chinese offensive language detection. In a few-shot learning scenario, however, our study shows promising prospects for non-English offensive language detection with limited resources. Our findings highlight the importance of cross-cultural transfer learning in improving offensive language detection and promoting inclusive digital spaces.

UR - http://www.scopus.com/inward/record.url?scp=85174993994&partnerID=8YFLogxK

U2 - 10.18653/v1/2023.c3nlp-1.2

DO - 10.18653/v1/2023.c3nlp-1.2

M3 - Article in proceedings

AN - SCOPUS:85174993994

SP - 8

EP - 15

BT - EACL 2023 - Cross-Cultural Considerations in NLP @ EACL, Proceedings of the Workshop

PB - Association for Computational Linguistics (ACL)

T2 - 1st Workshop on Cross-Cultural Considerations in NLP, C3NLP 2023

Y2 - 5 May 2023

ER -

ID: 372613556