Neural data-to-text generation models have achieved significant advancement in recent years. However, these models have two shortcomings: the generated texts tend to miss some vital information, and they often generate descriptions that are not consistent with the structured input data. To alleviate these problems, we propose a Neural data-to-text generation model with Dynamic content Planning, named NDP ² for abbreviation. The NDP can utilize the previously generated text to dynamically select the appropriate entry from the given structured data. We further design a reconstruction mechanism with a novel objective function that can reconstruct the whole entry of the used data sequentially from the hidden states of the decoder, which aids the accuracy of the generated text. Empirical results show that the NDP achieves superior performance over the state-of-the-art on ROTOWIRE and NBAZHN datasets, in terms of relation generation (RG), content selection (CS), content ordering (CO) and BLEU metrics. The human evaluation result shows that the texts generated by the proposed NDP are better than the corresponding ones generated by NCP in most of time. And using the proposed reconstruction mechanism, the fidelity of the generated text can be further improved significantly.

近年来，神经数据到文本生成模型取得了重大进展。但是，这些模型有两个缺点：生成的文本往往会丢失一些重要信息，并且它们通常会生成与结构化输入数据不一致的描述。为了解决这些问题，我们提出了一个ň与eural数据到文本代车型d ynamic内容P兰宁，名为NDP ²缩写。NDP可以利用先前生成的文本从给定的结构化数据中动态选择适当的条目。我们进一步设计了一种具有新颖目标函数的重构机制，该函数可以根据解码器的隐藏状态顺序重构所用数据的整个条目，从而有助于生成文本的准确性。实验结果表明，在关系生成（RG），内容选择（CS），内容排序（CO）和BLEU度量方面，NDP在ROTOWIRE和NBAZHN数据集上的表现优于最新技术。人工评估结果表明，在大多数情况下，拟议的NDP生成的文本要优于NCP生成的相应文本。并使用建议的重建机制，