Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation
This addresses a domain-specific bottleneck in dialogue systems for generating responses with multiple attributes, but it is incremental as it builds on existing controllable generation methods.
The paper tackles the problem of multi-attribute controllable dialogue generation lacking generalization to unseen attribute combinations, proposing a prompt-based disentangled model that improves performance on benchmarks.
Existing controllable dialogue generation work focuses on the single-attribute control and lacks generalization capability to out-of-distribution multiple attribute combinations. In this paper, we explore the compositional generalization for multi-attribute controllable dialogue generation where a model can learn from seen attribute values and generalize to unseen combinations. We propose a prompt-based disentangled controllable dialogue generation model, DCG. It learns attribute concept composition by generating attribute-oriented prompt vectors and uses a disentanglement loss to disentangle different attributes for better generalization. Besides, we design a unified reference-free evaluation framework for multiple attributes with different levels of granularities. Experiment results on two benchmarks prove the effectiveness of our method and the evaluation metric.