Key

Berkeley Institute of Design

Fall 2019 Seminar Series

Tuesdays 12-1pm, BiD Lab Hearst Memorial Mining Building 354/360

The BiD Seminar Series is a weekly graduate-level seminar that probes topics spanning human-computer interaction, mechanical design, education, architecture and art practice.

Invited speakers join us from academia, industry, research, and practice from around the world. The seminar is open to the Berkeley community and the general public.

Next up ...

The Role of Semantics and Natural language in Visual Analytical Workflows

10 December, 12-1 PM, BiD Lab

Vidya Setlur
Tableau Research Scientist

I am a staff research scientist at Tableau Software. I earned my doctorate in Computer Graphics in 2005 at Northwestern University. I love pushing the boundaries of product innovation in a principled fashion drawing from both research and engineering. My research interests lie at the intersection of natural language processing and computer graphics. In particular, the goal of my work is to develop new computer algorithms and user interfaces that enhance visual communication and understanding of the semantics of the underlying data. My research combines concepts and methods from information retrieval, human perception and cognitive science to help users effectively interact with devices and information in their environment. A significant portion of my work covers investigation, prototyping and evaluation of such novel concepts.

Since joining Tableau Research in 2012, I have worked on various projects and prototypes involving semantics and visual representation such as semantic icon encoding and semantically resonant color palettes. Most recently, I have been interested in exploring analytical conversation using natural language interaction via a system called Eviza. Subsequently, as part of productizing Tableau’s natural language feature, Ask Data, I moved to engineering and was a manager on the Natural Language Team at Tableau Software. There, I focused primarily on developing the theory and engineering of user intent in analytical conversation to provide analytically useful interpretations of users’ utterances among other things. With a couple of releases of the feature, I have moved back to research to explore medium and longer term natural language product initiatives at Tableau. I am also passionate about driving telemetry efforts at Tableau starting with Ask Data, and determining ways to instrument and consume usage data to further improve the product.

[...]

Upcoming Talks

Previous Talks

Previous Seminars