arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2004.07426cs.CL
收藏

基于动态内容规划的神经元数据到文本生成

Neural Data-to-Text Generation with Dynamic Content Planning

Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));Beijing Baidu Netcom Science Technology Co., Ltd.(北京百度网讯科技有限公司);University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校)

Kai Chen, Fayuan Li, Baotian Hu, Weihua Peng, Qingcai Chen, Hong Yu

摘要:

近年来,神经数据到文本生成模型取得了重大进展。然而,这些模型有两个缺点:生成的文本往往会遗漏一些重要的信息,并且它们经常生成与结构化输入数据不一致的描述。为了缓解这些问题,我们提出了一个神经数据到文本生成模型与动态内容规划,简称NDP。NDP可以利用先前生成的文本来从给定的结构化数据中动态地选择适当的条目。我们进一步设计了一个重建机制,一个新的目标函数,可以重建整个条目的使用数据顺序从隐藏状态的解码器,这有助于生成的文本的准确性。实证结果表明,NDP实现了优越的性能,在国家的最先进的ROTOWIRE数据集,在关系生成(RG),内容选择(CS),内容排序(CO)和BLEU指标。人工评价结果表明,在大多数情况下,NDP生成的文本优于NCP生成的文本。使用所提出的重建机制,生成的文本的保真度可以进一步显着提高。

英文摘要:

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 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 dataset, 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.

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。

↑