arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.01081cs.PL
收藏

基于类型导向的自然语言可视化合成

Type-Directed Synthesis of Visualizations from Natural Language Queries

Qiaochu Chen, Shankara Pailoor, Celeste Barnaby, Abby Criswell, Chenglong Wang, Greg Durrett, Isil Dillig

摘要:

我们提出了一种新的技术,基于程序合成自动生成可视化从自然语言查询。我们的方法解析的自然语言查询到一个细化类型规范使用的意图和插槽的范例,并利用类型导向合成生成一组可视化程序,最有可能满足用户的意图。我们的细化类型的系统捕获有用的提示存在于自然语言查询,并允许合成算法拒绝可视化违反完善的设计准则的输入数据集。我们已经在一个名为Graphy的工具中实现了我们的想法,并在NLVCorpus上对其进行了评估,NLVCorpus由3个流行的数据集和700多个真实世界的自然语言查询组成。我们的实验表明,Graphy显着优于最先进的基于自然语言的可视化工具,包括Transformer和基于规则的。

英文摘要:

We propose a new technique based on program synthesis for automatically generating visualizations from natural language queries. Our method parses the natural language query into a refinement type specification using the intents-and-slots paradigm and leverages type-directed synthesis to generate a set of visualization programs that are most likely to meet the user's intent. Our refinement type system captures useful hints present in the natural language query and allows the synthesis algorithm to reject visualizations that violate well-established design guidelines for the input data set. We have implemented our ideas in a tool called Graphy and evaluated it on NLVCorpus, which consists of 3 popular datasets and over 700 real-world natural language queries. Our experiments show that Graphy significantly outperforms state-of-the-art natural-language-based visualization tools, including transformer and rule-based ones.

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。

↑