Latent-optimized adversarial neural transfer for sarcasm detection

• Main Authors: Guo, Xu, Li, Boyang, Yu, Han, Miao, Chunyan
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2021
• Subjects: Engineering::Computer science and engineering; Transfer Learning; Deep Learning Optimization; Sarcasm Detection
• Online Access: https://aclanthology.org/volumes/2021.naacl-main/; https://hdl.handle.net/10356/153544
• Institution: Nanyang Technological University

The existence of multiple datasets for sarcasm detection prompts us to apply transfer learning to exploit their commonality. The adversarial neural transfer (ANT) framework utilizes multiple loss terms that encourage the source-domain and the target-domain feature distributions to be similar while o...