Towards Zero-Shot Personalized Table-to-Text Generation with Contrastive Persona Distillation
This addresses the problem of generating personalized text from tables for applications like chatbots or reports, but it is incremental as it builds on existing neural methods.
The paper tackles personalized table-to-text generation without requiring aligned persona-table-text datasets, proposing a semi-supervised method with contrastive persona distillation that achieves high content fidelity and personalized expressions in experiments on two benchmarks.
Existing neural methods have shown great potentials towards generating informative text from structured tabular data as well as maintaining high content fidelity. However, few of them shed light on generating personalized expressions, which often requires well-aligned persona-table-text datasets that are difficult to obtain. To overcome these obstacles, we explore personalized table-to-text generation under a zero-shot setting, by assuming no well-aligned persona-table-text triples are required during training. To this end, we firstly collect a set of unpaired persona information and then propose a semi-supervised approach with contrastive persona distillation (S2P-CPD) to generate personalized context. Specifically, tabular data and persona information are firstly represented as latent variables separately. Then, we devise a latent space fusion technique to distill persona information into the table representation. Besides, a contrastive-based discriminator is employed to guarantee the style consistency between the generated context and its corresponding persona. Experimental results on two benchmarks demonstrate S2P-CPD's ability on keeping both content fidelity and personalized expressions.