Abstract
Zero-shot cross-lingual transfer learning has been shown to be highly challenging for tasks involving a lot of linguistic specificities or when a cultural gap is present between lan- guages, such as in hate speech detection. In this paper, we highlight this limitation for hate speech detection in several domains and languages using strict experimental settings. Then, we propose to train on multilingual auxiliary tasks – sentiment analysis, named entity recognition, and tasks relying on syntactic information – to improve zero-shot transfer of hate speech detection models across languages. We show how hate speech detection models benefit from a cross-lingual knowledge proxy brought by auxiliary tasks fine-tuning and highlight these tasks’ positive impact on bridging the hate speech linguistic and cultural gap between languages.- Anthology ID:
- 2022.findings-aacl.33
- Volume:
- Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
- Month:
- November
- Year:
- 2022
- Address:
- Online only
- Editors:
- Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 347–363
- Language:
- URL:
- https://aclanthology.org/2022.findings-aacl.33
- DOI:
- Cite (ACL):
- Syrielle Montariol, Arij Riabi, and Djamé Seddah. 2022. Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models. In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022, pages 347–363, Online only. Association for Computational Linguistics.
- Cite (Informal):
- Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models (Montariol et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2022.findings-aacl.33.pdf