使用内容匹配约束实现基于神经表的文本生成（CS CL）---Elva

从知识库生成文本的目的是将知识三元组转换为自然语言描述，但现有的大多数方法忽略了生成的文本描述和原始表之间的忠实性，导致生成的信息超出了表的内容。本文首次提出了一种新颖的基于变压器的生成框架来实现忠实性这一目标，该方法的核心技术包括一个表-文本最优传输匹配损失和一个基于变压器模型的表-文本嵌入相似度损失，此外，为了评估忠实度，我们提出了一种新的自动度量方法，专门用于基于表的生成问题。在实验中，我们还对模型的各个组成部分进行了详细的分析，自动评估和人工评估都表明，我们的框架的表现大大优于现有最新技术。

原文题目：Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints

原文：Text generation from a knowledge base aims to translate knowledge triples to natural language descriptions. Most existing methods ignore the faithfulness between a generated text description and the original table, leading to generated information that goes beyond the content of the table. In this paper, for the first time, we propose a novel Transformer-based generation framework to achieve the goal. The core techniques in our method to enforce faithfulness include a new table-text optimal-transport matching loss and a table-text embedding similarity loss based on the Transformer model. Furthermore, to evaluate faithfulness, we propose a new automatic metric specialized to the table-to-text generation problem. We also provide detailed analysis on each component of our model in our experiments. Automatic and human evaluations show that our framework can significantly outperform state-of-the-art by a large margin.

原文作者：Zhenyi Wang, Xiaoyang Wang, Bang An, Dong Yu, Changyou Chen

原文链接：https://arxiv.org/abs/2005.00969