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

Authors

  • Zhiliang Tian Hong Kong University of Science and Technology HKUST Xiao-i Robot Joint Lab
  • Wei Bi Tencent AI Lab
  • Zihan Zhang Hong Kong University of Science and Technology
  • Dongkyu Lee Hong Kong University of Science and Technology
  • Yiping Song National University of Defense Science and Technology
  • Nevin L. Zhang Hong Kong University of Science and Technology HKUST Xiao-i Robot Joint Lab

Keywords:

Conversational AI/Dialog Systems, Generation

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.

Downloads

Published

2021-05-18

How to Cite

Tian, Z., Bi, W., Zhang, Z., Lee, D., Song, Y., & Zhang, N. L. (2021). Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15), 13907-13915. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17638

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing II