# Towards Zero-Shot Personalized Table-to-Text Generation with Contrastive Persona Distillation

arXiv: https://arxiv.org/abs/2304.08911 · HTML: https://mlsanity.com/paper/2304.08911/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 18 Apr 2023.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Minimum Risk Training for Neural Machine Translation](https://mlsanity.com/paper/1512.02433/) (2015)
- [Long and Diverse Text Generation with Planning-based Hierarchical Variational Model](https://mlsanity.com/paper/1908.06605/) (2019)
- [Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints](https://mlsanity.com/paper/2005.00969/) (2020)
- [Data-to-text Generation with Entity Modeling](https://mlsanity.com/paper/1906.03221/) (2019)
- [Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning](https://mlsanity.com/paper/2102.03554/) (2021)
- [Towards Knowledge-Based Personalized Product Description Generation in E-commerce](https://mlsanity.com/paper/1903.12457/) (2019)
- [Variational Template Machine for Data-to-Text Generation](https://mlsanity.com/paper/2002.01127/) (2020)
- [Probing Product Description Generation via Posterior Distillation](https://mlsanity.com/paper/2103.01594/) (2021)
- [User-Inspired Posterior Network for Recommendation Reason Generation](https://mlsanity.com/paper/2102.07919/) (2021)
- [Outline Generation: Understanding the Inherent Content Structure of Documents](https://mlsanity.com/paper/1905.10039/) (2019)
- [Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce](https://mlsanity.com/paper/1904.01735/) (2019)

## Abstract (arXiv)

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.