NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queries
NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queries
复制标题
DOI：
10.1109/tvcg.2020.3030378
复制
发表时间：
2020-08
影响因子：
5.2
通讯作者：
Arpit Narechania;Arjun Srinivasan;J. Stasko
中科院分区：
文献类型：
--
作者：
Arpit Narechania;Arjun Srinivasan;J. Stasko
自然语言界面（NLls）在可视化数据分析方面展现出了巨大的前景，允许人们灵活地指定可视化并与之交互。然而，开发可视化 NLI 仍然是一项具有挑战性的任务，需要自然语言处理 (NLP) 技术的低级实现以及视觉分析任务和可视化设计的知识。我们推出了 NL4DV，一个用于自然语言驱动的数据可视化的工具包。 NL4DV 是一个 Python 包，它将表格数据集和有关该数据集的自然语言查询作为输入。作为响应，该工具包返回一个建模为 JSON 对象的分析规范，其中包含数据属性、分析任务以及与输入查询相关的 Vega-Lite 规范列表。在此过程中，NL4DV 可以帮助没有 NLP 背景的可视化开发人员，使他们能够创建新的可视化 NLI 或将自然语言输入合并到现有系统中。我们通过四个示例演示 NL4DV 的用法和功能：1）在 Jupyter Notebook 中使用自然语言渲染可视化，2）开发 NLI 来指定和编辑 Vega-Lite 图表，3）从 DataTone 系统重新创建数据歧义小部件，以及 4）合并语音输入以创建多模式可视化系统。
Natural language interfaces (NLls) have shown great promise for visual data analysis, allowing people to flexibly specify and interact with visualizations. However, developing visualization NLIs remains a challenging task, requiring low-level implementation of natural language processing (NLP) techniques as well as knowledge of visual analytic tasks and visualization design. We present NL4DV, a toolkit for natural language-driven data visualization. NL4DV is a Python package that takes as input a tabular dataset and a natural language query about that dataset. In response, the toolkit returns an analytic specification modeled as a JSON object containing data attributes, analytic tasks, and a list of Vega-Lite specifications relevant to the input query. In doing so, NL4DV aids visualization developers who may not have a background in NLP, enabling them to create new visualization NLIs or incorporate natural language input within their existing systems. We demonstrate NL4DV's usage and capabilities through four examples: 1) rendering visualizations using natural language in a Jupyter notebook, 2) developing a NLI to specify and edit Vega-Lite charts, 3) recreating data ambiguity widgets from the DataTone system, and 4) incorporating speech input to create a multimodal visualization system.