Toxicity Detection in Finnish Using Machine Translation

Anni Eskelinen, Laura Silvala, Filip Ginter, Sampo Pyysalo, Veronika Laippala


Abstract
Due to the popularity of social media platforms and the sheer amount of user-generated content online, the automatic detection of toxic language has become crucial in the creation of a friendly and safe digital space. Previous work has been mostly focusing on English leaving many lower-resource languages behind. In this paper, we present novel resources for toxicity detection in Finnish by introducing two new datasets, a machine translated toxicity dataset for Finnish based on the widely used English Jigsaw dataset and a smaller test set of Suomi24 discussion forum comments originally written in Finnish and manually annotated following the definitions of the labels that were used to annotate the Jigsaw dataset. We show that machine translating the training data to Finnish provides better toxicity detection results than using the original English training data and zero-shot cross-lingual transfer with XLM-R, even with our newly annotated dataset from Suomi24.
Anthology ID:
2023.nodalida-1.68
Volume:
Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
Month:
May
Year:
2023
Address:
Tórshavn, Faroe Islands
Venue:
NoDaLiDa
SIG:
Publisher:
University of Tartu Library
Note:
Pages:
685–697
Language:
URL:
https://aclanthology.org/2023.nodalida-1.68
DOI:
Bibkey:
Cite (ACL):
Anni Eskelinen, Laura Silvala, Filip Ginter, Sampo Pyysalo, and Veronika Laippala. 2023. Toxicity Detection in Finnish Using Machine Translation. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 685–697, Tórshavn, Faroe Islands. University of Tartu Library.
Cite (Informal):
Toxicity Detection in Finnish Using Machine Translation (Eskelinen et al., NoDaLiDa 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/2023.nodalida-1.68.pdf