面向低资源场景下基于少样本学习的跨语言音频滥用内容检测
Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learning
AI总结：
本研究针对低资源场景下音频滥用内容检测研究不足的问题，结合Wav2Vec、Whisper等预训练模型表示与MAML框架，基于ADIMA数据集用少样本学习实现10种印度语言的滥用内容检测，验证了预训练模型的低资源泛化能力。
摘要：
在线滥用内容检测，尤其是低资源场景下的音频模态检测，目前仍未得到充分研究。我们探究了预训练音频表示在低资源语言（本研究中为印度语言）中检测滥用语言的潜力，采用了少样本学习（Few Shot Learning, FSL）方法。我们利用Wav2Vec、Whisper等模型的强表示能力，结合ADIMA数据集与FSL开展跨语言滥用内容检测研究。我们的方法将这些表示集成到模型无关元学习（Model-Agnostic Meta-Learning, MAML）框架中，实现10种语言的滥用语言分类。我们在50-200的不同样本量下开展实验，评估有限数据对性能的影响。此外，我们还进行了特征可视化研究以更好地理解模型行为。本研究凸显了预训练模型在低资源场景下的泛化能力，为多语言语境下的滥用语言检测提供了宝贵见解。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
