NL4DV-Stylist: Styling Data Visualizations Using Natural Language and Example Charts

Natural language interfaces (NLIs) enable flexible authoring and interaction with visualizations (VIS) using natural language (NL). However, current NLIs predominantly focus on identifying the data attributes and analytic tasks from the user's query and give less emphasis to customizing the design of the output visualizations, which is an important consideration to satisfy personal preferences, meet branding requirements, and/or ensure accessibility. We present NL4DV-Stylist, a Python toolkit that utilizes example charts and NL instructions as design guidance, enhancing current NL to VIS authoring workflows to produce more design-informed visualizations. For instance, if a user generally prefers horizontal legends or wants to re-use the blue color scheme they saw in a scatterplot, they can supply these as inputs to the toolkit, which will incorporate these design preferences when generating visualizations. NL4DV-Stylist is available as open-source software at https://nl4dv.github.io.