Zhiyu Chen, Harini Eavani, Wenhu Chen, Yinyin Liu, William Yang Wang
TL;DR该文提出了少样本自然语言生成(Few-shot natural language generation)任务,设计了基于内容选择和语言建模的模型架构,表现良好。
Abstract
Neural-based end-to-end approaches to natural language generation (NLG) from
structured data or knowledge are data-hungry, making their adoption for
real-world applications difficult with limited data. In this wo