# Personalizing Dialogue Agents via Meta-Learning

## TL;DR

This paper introduces a meta-learning approach to personalize dialogue agents that adapts quickly to new users using minimal dialogue data, eliminating the need for manually crafted persona descriptions.

## Contribution

It extends MAML to personalized dialogue without relying on persona descriptions, enabling rapid adaptation with few dialogue samples.

## Key findings

- Outperforms non-meta-learning baselines on Persona-chat dataset
- Achieves higher human-evaluated fluency and consistency
- Demonstrates effective personalization without manual persona data

## 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.