Adversarial training using meta-learning for BERT

• Main Author: Low, Timothy Jing Haen
• Other Authors: Joty Shafiq Rayhan
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: https://hdl.handle.net/10356/156635
• Institution: Nanyang Technological University

Deep learning is currently the most successful method of semantic analysis in natural language processing. However, in recent years, many variants of carefully crafted inputs designed to cause misclassification, known as adversarial attacks, have been engineered with tremendous success. One well-...