XHate-999: Analyzing and Detecting Abusive Language Across Domains and Languages
Goran Glavaš, Vanja Mladen Karan, Ivan Vulić
Abstract
We present XHate-999, a multi-domain and multilingual evaluation data set for abusive language detection. By aligning test instances across six typologically diverse languages, XHate-999 for the first time allows for disentanglement of the domain transfer and language transfer effects in abusive language detection. We conduct a series of domain- and language-transfer experiments with state-of-the-art monolingual and multilingual transformer models, setting strong baseline results and profiling XHate-999 as a comprehensive evaluation resource for abusive language detection. Finally, we show that domain- and language-adaption, via intermediate masked language modeling on abusive corpora in the target language, can lead to substantially improved abusive language detection in the target language in the zero-shot transfer setups.
BibTeX
@inproceedings{glavas-etal-2020-xhate,
title = "{XH}ate-999: Analyzing and Detecting Abusive Language Across Domains and Languages",
author = "Glava{\v{s}}, Goran and
Karan, Vanja Mladen and
Vuli{\'c}, Ivan",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.559/",
doi = "10.18653/v1/2020.coling-main.559",
pages = "6350--6365"
}