arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.13756cs.CL
收藏

基于变分顺序规划的数据文本生成

Data-to-text Generation with Variational Sequential Planning

Institute for Language, Cognition and Computation(语言、认知与计算研究所);School of Informatics, University of Edinburgh(爱丁堡大学信息学院)

Ratish Puduppully, Yao Fu, Mirella Lapata

摘要:

我们认为,数据到文本生成,其目的是从非语言输入创建文本输出的任务。我们专注于生成长格式文本,即,文档与多个段落,并提出了一个神经模型增强与规划组件负责组织高层次的信息在一个连贯的和有意义的方式。我们推断潜在的计划顺序与结构化的变分模型,而交错的规划和生成的步骤。文本是通过对先前的变分决策和先前生成的文本进行调节而生成的。在两个数据到文本基准测试(RotoWire和MLB)上的实验表明,我们的模型优于强基线,并且在有限的训练数据(例如,几百例)。

英文摘要:

We consider the task of data-to-text generation, which aims to create textual output from non-linguistic input. We focus on generating long-form text, i.e., documents with multiple paragraphs, and propose a neural model enhanced with a planning component responsible for organizing high-level information in a coherent and meaningful way. We infer latent plans sequentially with a structured variational model, while interleaving the steps of planning and generation. Text is generated by conditioning on previous variational decisions and previously generated text. Experiments on two data-to-text benchmarks (RotoWire and MLB) show that our model outperforms strong baselines and is sample efficient in the face of limited training data (e.g., a few hundred instances).

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。

↑