Discovering User Groups for Natural Language Generation

TL;DR

This paper introduces a model that learns user groups for dialog systems, enabling personalized communication by dynamically identifying and adapting to different user understanding and expression styles.

Contribution

It proposes a novel approach to automatically discover user groups during training, improving personalized natural language generation without predefined group labels.

Findings

Successfully identifies user groups in dialog tasks

Learns to adapt communication strategies for different groups

Dynamically assigns new users to existing groups

Abstract

We present a model which predicts how individual users of a dialog system understand and produce utterances based on user groups. In contrast to previous work, these user groups are not specified beforehand, but learned in training. We evaluate on two referring expression (RE) generation tasks; our experiments show that our model can identify user groups and learn how to most effectively talk to them, and can dynamically assign unseen users to the correct groups as they interact with the system.