Welcome to the iGraph-Lite page
iGraph-Lite is an extensible system that generates natural language
descriptions of statistical graphs, particularly those created for
Statistics Canada online publication, "The Daily". iGraph-Lite reads a
graph from a set of graphing programs, builds intermediate
representations of it in several formats (XML, CouchDB and OWL) and
outputs a description using NLG algorithms over a "string template"
iGraph is a collaborative research effort and has involved several
people along the years.
Current members of the iGraph team include:
- Leo Ferres (PI, Universidad de Concepción, Chile, and Carleton
- Martin Lachance (Accessibility, Dissemination Division, Statistics
- Louis Boucher (Dissemination Division, Statistics Canada)
- Diego Caro (Computer Science, Universidad de Concepción)
- Michael Soza (Computer Science, Universidad de Concepción)
- Patricio Sandaña (Computer Science, Universidad de Concepción)
- Gitte Lindgaard (Carleton University, Canada)
- Livia Sumegi (Carleton University, Canada)
- Petro Verkhogliad (Carleton University, Canada)
We have been able to gather 500+ graphs from Statistics Canada from
The Daily, and the descriptions generated automatically for these
graphs are available here. This gives a good idea of the type of
generation in both English and French, together with constituting a
good repository for blind and visuall-impaired people to check out the
graphs that have been published already.
iGraph is in a constant state of flux, much of the work is somewhat
experimental and geared towards the graphs produced by Statistics
Canada. If anyone would like to contribute to the efforts and make
iGraph more general purpose, please let me know and I will grant you
access to the source repository.
- Ferres, L., Lindgaard, G.,Sumegi,
L. 2010. Evaluating a tool for improving accessibility to complex visual objects. In
Proceedings of the 12th international ACM SIGACCESS Conference on
Computers and Accessibility (Orlando, Florida, USA, October 25—27,
2019). Assets '10. ACM, New York, NY. (Pre-print version. Final
version will be available from the ACM DL in late October.), see the
- Ferres, L., Verkhogliad, P., Sumegi, L., Boucher, L., Lachance, M.,
G. 2008. A syntactic analysis of accessibility to a corpus of statistical graphs
In Proceedings of the 2008 international Cross-Disciplinary
Conference on Web Accessibility (W4A) (Beijing, China, April 21-22,
2008). W4A '08, vol. 317. ACM, New York, NY, 37-44.
- Leo Ferres, Petro Verkhogliad, Gitte Lindgaard, Louis Boucher,
Antoine Chretien, Martin Lachance:
Improving accessibility to statistical graphs: the iGraph-Lite system. Proceedings
of the 2007 ACM ASSETS Conference, October 2007: 67-74.
- Leo Ferres, Avi Parush, Shelley Roberts, Gitte Lindgaard:
Helping People with Visual Impairments Gain Access to Graphical Information Through Natural Language: The iGraph System. Proceedings
of ICCHP 2006: 1122-1130.
- Ferres, L., Verkhogliad, P., and Boucher, L. 2007. (Natural
language) interaction with graphical representations of statistical
data. In Proceedings of the 2007 international Cross-Disciplinary
Conference on Web Accessibility (W4a) (Banff, Canada, May 07 - 08,
2007). W4A '07, vol. 225. ACM, New York, NY, 132-133. [Judges'
Prize, best accessibility tool].
|The W4A Prize|
Mon Jul 19 10:51:14 2010