Generating personalized dialogue via multi-task meta-learning

• 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: 2021
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Multi-Task Meta-Learning; Personalized Dialogue Generation
• Online Access: https://semdial2021.ling.uni-potsdam.de/assets/semdial2021_potsdial_full_proceedings.pdf; https://hdl.handle.net/10356/153442
• Institution: Nanyang Technological University

Conventional approaches to personalized dialogue generation typically require a large corpus, as well as predefined persona information. However, in a real-world setting, neither a large corpus of training data nor persona information are readily available. To address these practical limitations, we propose a novel multi-task meta-learning approach which involves training a model to adapt to new personas without relying on a large corpus, or on any predefined persona information. Instead, the model is tasked with generating personalized responses based on only the dialogue context. Unlike prior work, our approach leverages on the provided persona information only during training via the introduction of an auxiliary persona reconstruction task. In this paper, we introduce 2 frameworks that adopt the proposed multi-task meta-learning approach: the Multi-Task MetaLearning (MTML) framework, and the Alternating Multi-Task Meta-Learning (AMTML) framework. Experimental results show that utilizing MTML and AMTML results in dialogue responses with greater persona consistency.