Partially randomizing transformer weights for dialogue response diversity

• 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: 2023
• Subjects: Engineering::Electrical and electronic engineering; Transformer; Response
• Online Access: https://hdl.handle.net/10356/172416; https://paclic2023.github.io/
• Institution: Nanyang Technological University

Despite recent progress in generative open-domain dialogue, the issue of low response diversity persists. Prior works have addressed this issue via either novel objective functions, alternative learning approaches such as variational frameworks, or architectural extensions such as the Randomized...