arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.12467cs.CL
收藏

R2D2:具有替换检测的健壮数据到文本转换

R2D2: Robust Data-to-Text with Replacement Detection

Yale University(耶鲁大学)

Linyong Nan, Lorenzo Jaime Yu Flores, Yilun Zhao, Yixin Liu, Luke Benson, Weijin Zou, Dragomir Radev

摘要:

不忠实文本生成是文本生成系统中的一个常见问题。在数据到文本(D2T)系统的情况下,生成的文本的真实性对于任何现实世界的应用程序都特别重要。我们介绍了R2D2,这是一个训练框架,它通过训练一个系统作为生成器和一个具有额外的替换检测和不可能学习任务的忠实度测试器来解决不忠实的数据到文本生成问题。为了促进这种训练,我们提出了两种方法来采样不忠实的句子。我们认为,差的实体检索能力的D2T系统是不忠实的主要来源之一,所以除了现有的指标,我们进一步提出了基于NER的指标来评估D2T代的保真度。我们的实验结果表明,R2D2系统可以有效地减轻不忠实的文本生成,并在FeTaQA,LogicNLG和ToTTo上实现了新的最先进的结果,所有这些都有显着的改进。

英文摘要:

Unfaithful text generation is a common problem for text generation systems. In the case of Data-to-Text (D2T) systems, the factuality of the generated text is particularly crucial for any real-world applications. We introduce R2D2, a training framework that addresses unfaithful Data-to-Text generation by training a system both as a generator and a faithfulness discriminator with additional replacement detection and unlikelihood learning tasks. To facilitate such training, we propose two methods for sampling unfaithful sentences. We argue that the poor entity retrieval capability of D2T systems is one of the primary sources of unfaithfulness, so in addition to the existing metrics, we further propose NER-based metrics to evaluate the fidelity of D2T generations. Our experimental results show that R2D2 systems could effectively mitigate the unfaithful text generation, and they achieve new state-of-the-art results on FeTaQA, LogicNLG, and ToTTo, all with significant improvements.

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。

↑