Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learning

Aditya Narayan Sankaran, Reza Farahbakhsh, Noel Crespi

Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learning: 2 upvotes on Hugging Face Daily Papers, #29 of 29 papers on 2024-12-03. Day-by-day upvote history.

Online abusive content detection, particularly in low-resource settings and within the audio modality, remains underexplored. We investigate the potential of pre-trained audio representations for detecting abusive language in low-resource languages, in this case, in Indian languages using Few Shot Learning (FSL). Leveraging powerful representations from models such as Wav2Vec and Whisper, we explore cross-lingual abuse detection using the ADIMA dataset with FSL. Our approach integrates these representations within the Model-Agnostic Meta-Learning (MAML) framework to classify abusive language in 10 languages. We experiment with various shot sizes (50-200) evaluating the impact of limited data on performance. Additionally, a feature visualization study was conducted to better understand model behaviour. This study highlights the generalization ability of pre-trained models in low-resource scenarios and offers valuable insights into detecting abusive language in multilingual contexts.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.