Generating Personalized Dialogue via Multi-Task Meta-Learning
This work addresses the practical limitation of data scarcity and lack of persona information in real-world personalized dialogue systems, offering a novel method for adaptation.
The paper tackles the problem of generating personalized dialogue without requiring large training corpora or predefined persona information at test time, by proposing a multi-task meta-learning approach that uses an auxiliary persona reconstruction task during training; experimental results show that their frameworks, MTML and AMTML, produce dialogue responses with greater persona consistency.
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 Meta-Learning (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.