Virtual prompt pre-training for prototype-based few-shot relation extraction

• Main Authors: He, Kai, Huang, Yucheng, Mao, Rui, Gong, Tieliang, Li, Chen, Cambria, Erik
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering; Few-shot Learning; Information Extraction
• Online Access: https://hdl.handle.net/10356/170494
• Institution: Nanyang Technological University

Prompt tuning with pre-trained language models (PLM) has exhibited outstanding performance by reducing the gap between pre-training tasks and various downstream applications, which requires additional labor efforts in label word mappings and prompt template engineering. However, in a label intensive...