Cross-lingual transfer and multilingual learning for detecting harmful behaviour in African under-resourced language dialogue
Ajayi, Tunde Oluwaseyi Arcan, Mihael Buitelaar, Paul
Ajayi, Tunde Oluwaseyi
Arcan, Mihael
Buitelaar, Paul
Loading...
Repository DOI
Publication Date
2024-09-18
Keywords
Type
conference paper
Downloads
Citation
Tunde, Oluwaseyi Ajayi, Arcan, Mihael, & Buitelaar, Paul. (2024). Cross-lingual transfer and multilingual learning for detecting harmful behaviour in African under-resourced language dialogue. Paper presented at the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Kyoto, Japan, 18-20 September. https://doi.org/10.18653/v1/2024.sigdial-1.49
Abstract
Most harmful dialogue detection models are de veloped for high-resourced languages. Consequently, users who speak under-resourced lan guages cannot fully benefit from these models in terms of usage, development, detection and mitigation of harmful dialogue utterances. Our work aims at detecting harmful utterances in under-resourced African languages. We lever age transfer learning using pretrained models trained with multilingual embeddings to de velop a cross-lingual model capable of detect ing harmful content across various African lan guages. We first fine-tune a harmful dialogue detection model on a selected African dialogue dataset. Additionally, we fine-tune a model on a combined dataset in some African lan guages to develop a multilingual harmful dia logue detection model. We then evaluate the cross-lingual model’s ability to generalise to an unseen African language by performing harm ful dialogue detection in an under-resourced language not present during pretraining or fine tuning. We evaluate our models on the test datasets. We show that our best performing models achieve impressive results in terms of F1 score. Finally, we discuss the results and limitations of our work.
Publisher
Association for Computational Linguistics
Publisher DOI
https://doi.org/10.18653/v1/2024.sigdial-1.49