Cross-lingual offensive speech identification with transfer learning for low-resource languages. (July 2022)

• Record Type: Journal Article
• Authors: Shi, Xiayang; Liu, Xinyi; Xu, Chun; Huang, Yuanyuan; Chen, Fang; Zhu, Shaolin
• Is Part Of: Computers & electrical engineering. Volume 101(2022)
• Publication Date: 2022-07
• Subjects: Offensive speech -- Low-resource languages -- Cross-lingual -- Transfer learning -- Adversarial learning; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108005
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Most of research on the identification of offensive speech on social media platforms exist in English and other rich languages. A series of recently proposed methods for detecting low-resource offensive languages require labeled data. In this work, we propose an unsupervised model that can detect offensive speech for low-resource languages. Our method does not depend on any labeled data of low-resource languages. In detail, we propose an agreement regularized training that combines adversarial learning and transfer learning. Augmenting low-resource training data with sample regeneration methods to maintain the performance of the trained offensive speech identification model from rich-resource to low-resource languages. Extensive experiments on four low-resource languages demonstrate that our model either is on par or outperforms the supervised methods, without employing any annotated data on real-world offensive speech detection tasks for low-resource languages. Graphical abstract: