papers AI Learner
The Github is limit! Click to go to the new site.

Personalizing Dialogue Agents via Meta-Learning

2019-05-24
Zhaojiang Lin, Andrea Madotto, Chien-Sheng Wu, Pascale Fung

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.10033

PDF

http://arxiv.org/pdf/1905.10033


Similar Posts

Comments