(Natural language) interaction with graphical representations of statistical data

Abstract

Numerical information is often presented in graphs to take advantage of the human ability to quickly find visual patterns. Unfortunately, this medium is problematic for people who are blind or otherwise visually-impaired. To provide accessibility to graphs published in The Daily (Statistics Canada's main dissemination venue), we have developed iGraph, a system that provides short verbal descriptions of the information depicted in graphs and a way of also interacting with graphical information.

A syntactic analysis of accessibility to a corpus of statistical graphs

“…valueSet behaves similarly to categorySet in Rule (7). In turn, trendline is defined as trendlines → trendline * .…”

“…In previous work [5,6,7,8], we have reported on the design and implementation of iGraph-Lite, a system that helps with the the problems of image structuring of statistical graphs [17] and the automation of content creation for alt and longdes attributes. During stress-testing of this work, however, it was evident that graphs were not only inaccessible as raster images, but also at deeper levels of representation.…”