Program

All listed times are in USA Central Time (UTC-5)

8 - 9am Opening + Keynote
Nate Nichols
Chief Scientist |

Automated Data Storytelling: Scaling Data-driven Understanding and Action to Business Users

Recent years have seen massive investments and improvements in various components of the modern business intelligence stack, but many of these advances have not benefited the business users we expect to consume and act on the information: only a third report getting insights in a way that is meaningful to them. This fact causes widespread disappointment and frustration in many organizations today. We believe the issue lies primarily with the presentation layer: dashboards deliver visualizations at scale but are too difficult to extract information and insights from for all but the most technical and determined of users. While alternative delivery methods exist (e.g. data storytelling), the time-consuming process of creating them has limited their reach historically. Fortunately, advances in NLP now enable the automated generation of data-driven narratives as well as a more “push”-oriented user experience that helps point users to where their attention and effort is needed most. Together, these capabilities deliver on the last mile of data understanding and allow organizations to unlock more of the returns from the investments they’ve made in their data and analytics technology and processes. This talk will discuss our automated data storytelling product Lexio and the current state of the art, as well as planned future work.

9 - 9.30am Paper Session I
  • Aunt Lily Can Say Her Visualizations: Directing Analysis, Design, and Storytelling in Natural Language (A Vision) [paper] [presentation]
    Zening Qu, Fan Du, Ryan Rossi, and Bill Howe
  • ONYX: Towards Extending Natural Language Interfaces for Data Visualization Tools through Interactive Task Learning [paper] [presentation]
    Marcel Ruoff, Brad A Myers, and Alexander Maedche
  • Visualising the News [paper] [presentation]
    Evelyn Matson, Daniel J. Barajas, Jose Corella, and David Guy Brizan
9.30 - 10am Coffee Break
10 - 10.20am Paper Session II
  • nvBench: A Large-Scale Synthesized Dataset for Cross-Domain Natural Language to Visualization Task [paper] [presentation]
    Yuyu Luo, Jiawei Tang, and Guoliang Li
  • Give Text A Chance: Advocating for Equal Consideration for Language and Visualization [paper] [presentation]
    Chase Stokes and Marti Hearst
10.20 - 11.20am Group Discussions
Here's the link to the topics of interest form.
11.20 - 11.30am Closing