Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks

TL;DR

This paper introduces a few-shot personalized conversation system leveraging social networks, enabling models to generate tailored responses for new users with limited data by learning from social connections.

Contribution

It proposes a meta-learning based PCM with a task aggregator that utilizes social networks to improve personalization for newcomers with scarce conversation data.

Findings

Outperforms baselines in response appropriateness.

Enhances response diversity and consistency.

Effective for new users with limited conversations.

Abstract

Personalized conversation models (PCMs) generate responses according to speaker preferences. Existing personalized conversation tasks typically require models to extract speaker preferences from user descriptions or their conversation histories, which are scarce for newcomers and inactive users. In this paper, we propose a few-shot personalized conversation task with an auxiliary social network. The task requires models to generate personalized responses for a speaker given a few conversations from the speaker and a social network. Existing methods are mainly designed to incorporate descriptions or conversation histories. Those methods can hardly model speakers with so few conversations or connections between speakers. To better cater for newcomers with few resources, we propose a personalized conversation model (PCM) that learns to adapt to new speakers as well as enabling new speakers to learn from resource-rich speakers. Particularly, based on a meta-learning based PCM, we propose a task aggregator (TA) to collect other speakers' information from the social network. The TA provides prior knowledge of the new speaker in its meta-learning. Experimental results show our methods outperform all baselines in appropriateness, diversity, and consistency with speakers.