Discovering User Groups for Natural Language Generation
This work addresses the challenge of personalized natural language generation for dialog systems, though it appears incremental as it builds on existing referring expression generation tasks.
The paper tackles the problem of generating natural language that adapts to individual users by automatically discovering user groups from interaction data, rather than using predefined groups. The model successfully identified user groups and learned effective communication strategies for them, achieving dynamic assignment of unseen users to appropriate groups during system interactions.
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.