Personalizing Dialogue Agents via Meta-Learning
This addresses the challenge of personalizing dialogue agents without costly hand-crafted data, though it is incremental as it builds on existing meta-learning methods.
The paper tackles the problem of expensive persona description collection for personalized dialogue agents by proposing a meta-learning approach that adapts to new personas using only a few dialogue samples, outperforming baselines in automatic and human evaluations.
Existing personalized dialogue models use human designed persona descriptions to improve dialogue consistency. Collecting such descriptions from existing dialogues is expensive and requires hand-crafted feature designs. In this paper, we propose to extend Model-Agnostic Meta-Learning (MAML)(Finn et al., 2017) to personalized dialogue learning without using any persona descriptions. Our model learns to quickly adapt to new personas by leveraging only a few dialogue samples collected from the same user, which is fundamentally different from conditioning the response on the persona descriptions. Empirical results on Persona-chat dataset (Zhang et al., 2018) indicate that our solution outperforms non-meta-learning baselines using automatic evaluation metrics, and in terms of human-evaluated fluency and consistency.