"Articulate: Creating Meaningful Visualizations from Natural Language (chapter)"
Articulate: Creating Meaningful Visualizations from Natural Language (chapter)
Sun, Y., Leigh, J., Johnson, A., Di Eugenio, B.
- Publication: IGI Global, pp 218-235
- Link: http://dx.doi.org/10.4018/978-1-4666-4309-3.ch011
- PDF: articulate_sun_fullchapter.pdf
Articulate displayed on EVL’s Cyber-Commons tiled display
Credit: L. Long, EVL
This chapter presents an approach to enable non-visualization experts to craft advanced visualizations through the use of natural language as the primary interface. The main challenge in this research is in determining how to translate imprecise verbal queries into effective visualizations. To demonstrate the viability of the concept, we developed and evaluated a prototype, Articulate, which allows users to simply ask the computer for questions about their data, and have it automatically generate visualizations that answer these questions. We discovered that by relieving the user of the burden of learning how to use a complex interface, we enable them to focus on articulating better scientific questions and wasting less time in producing unintended visualizations.