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 2102.02723cs.CL
收藏

使用宏规划生成数据到文本

Data-to-text Generation with Macro 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, Mirella Lapata

摘要:

最近的数据到文本生成方法已经采用了非常成功的编码器-解码器架构或其变体。这些模型生成的文本是流畅的(但通常不精确),在选择适当的内容和连贯地排序方面表现得很差。为了克服其中的一些问题,我们提出了一个神经模型与宏观规划阶段,其次是一个生成阶段,让人想起传统的方法,包括单独的模块规划和表面实现。宏观计划代表重要内容的高级组织,如实体,事件及其交互;它们从数据中学习并作为生成器的输入。在两个数据到文本基准测试(RotoWire和MLB)上的大量实验表明,我们的方法在自动和人工评估方面优于竞争基准。

英文摘要:

Recent approaches to data-to-text generation have adopted the very successful encoder-decoder architecture or variants thereof. These models generate text which is fluent (but often imprecise) and perform quite poorly at selecting appropriate content and ordering it coherently. To overcome some of these issues, we propose a neural model with a macro planning stage followed by a generation stage reminiscent of traditional methods which embrace separate modules for planning and surface realization. Macro plans represent high level organization of important content such as entities, events and their interactions; they are learnt from data and given as input to the generator. Extensive experiments on two data-to-text benchmarks (RotoWire and MLB) show that our approach outperforms competitive baselines in terms of automatic and human evaluation.

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。

↑