A randomized link transformer for diverse open-domain dialogue generation

• Main Authors: Lee, Jing Yang, Lee, Kong Aik, Gan, Woon-Seng
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2022
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Randomized Link Transformer; Open-Domain Dialogue Generation
• Online Access: https://hdl.handle.net/10356/159793; https://aclanthology.org/volumes/2022.nlp4convai-1/
• Institution: Nanyang Technological University

A major issue in open-domain dialogue generation is the agent’s tendency to generate repetitive and generic responses. The lack in response diversity has been addressed in recent years via the use of latent variable models, such as the Conditional Variational Auto-Encoder (CVAE), which typically inv...