基于渐进编辑的高召回率数据文本生成
High Recall Data-to-text Generation with Progressive Edit
摘要：
数据到文本（D2T）生成是从结构化输入生成文本的任务。我们观察到，当相同的目标句子被重复两次，Transformer（T5）的模型生成的输出由结构化的输入不对称的句子。换句话说，这些句子在长度和质量上都不同。我们称这种现象为“不对称生成”，并在D2T生成中利用这一点。一旦生成了不对称的句子，我们就在输出的第一部分添加一个不重复的目标。当这经过渐进式编辑（ProEdit）时，召回增加。因此，这种方法比编辑之前更好地覆盖了结构化输入。ProEdit是一种简单但有效的方法来提高D2T生成的性能，它在ToTTo数据集上实现了最新的结果
英文摘要：
Data-to-text (D2T) generation is the task of generating texts from structured inputs. We observed that when the same target sentence was repeated twice, Transformer (T5) based model generates an output made up of asymmetric sentences from structured inputs. In other words, these sentences were different in length and quality. We call this phenomenon "Asymmetric Generation" and we exploit this in D2T generation. Once asymmetric sentences are generated, we add the first part of the output with a no-repeated-target. As this goes through progressive edit (ProEdit), the recall increases. Hence, this method better covers structured inputs than before editing. ProEdit is a simple but effective way to improve performance in D2T generation and it achieves the new stateof-the-art result on the ToTTo dataset
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
