基于对比个性蒸馏的零样本个性化表格生成（英文版）

英文标题：Towards Zero-Shot Personalized Table-to-Text Generation with Contrastive Persona Distillation中文摘要：研究采用零样本的方式进行个性化表格文本生成，提出了一种半监督方法，利用对比个性蒸馏实现个性化内容。该方法旨在提高文本信息生成的个性化表现，同时维持内容的真实性，实验表明该方法表现出色。英文摘要：Existing neural methods have shown great potentials towards generatinginformative text from structured tabular data as well as maintaining highcontent fidelity. However, few of them shed light on generating personalizedexpressions, which often requires well-aligned persona-table-text datasets thata