Danielle Bragg (University of Washington)

Building Accessible Information Systems: A Data-Driven Approach

Computer scientists have made progress on many problems in information access: curating large datasets, developing machine learning techniques, building extensive networks, and designing interfaces to navigate various media. However, many of these solutions do not work well for people with disabilities, who total a billion worldwide (and nearly one in five in the US). For example, visual graphics and small text may exclude people with visual impairments, and text-based resources like search engines and text editors may not fully support people using unwritten sign languages.

In this talk, I will present three systems that expand and enrich access to information: 1) ASL-Search, an American Sign Language (ASL) dictionary trained on data from volunteer ASL students, 2) Smartfonts and Livefonts, scripts that reimagine the alphabet’s appearance to improve legibility for low-vision readers, and 3) ASL-Live, the first animated reading/writing system for ASL. These systems employ quantitative methods, using large-scale data collected through existing and novel crowdsourcing platforms to solve data scarcity problems and explore design spaces. They also involve people with disabilities in the solution process, to better understand and address accessibility problems.

About the Speaker

Danielle Bragg is a PhD candidate in Computer Science & Engineering at the University of Washington, advised by Richard Ladner. Her research focuses on building systems that improve access to information by leveraging modern computing capabilities in innovative ways. Her research interests combine human-computer interaction, accessibility, and applied machine learning. Her diverse past projects span computer music, data visualization, computational biology, applied mathematics, and network protocols. Before starting her PhD, she received her AB in Applied Mathematics from Harvard University.