Generating Explanatory Captions for Information Graphics
Abstract
Graphical presentations can be used to communi- cate information in relational data sets succinctly and effectively. However, novel graphical presen- tations about numerous attributes and their relation- ships are often difficult to understand completely until explained. Automatically generated graphical presentations must therefore either be limited to simple, conventional ones, or risk incomprehen- sibility. One way of alleviating this problem is to design graphical presentation systems that can work in conjunction with a natural language gener- ator to produce "explanatory captions." This paper presents three strategies for generating explanatory captions to accompany information graphics based on: (1) a representation of the structure of the graph- ical presentation (2) a framework for identifying the perceptual complexity of graphical elements, and (3) the structure of the data expressed in the graphic. We describe an implemented system and illustrate how it is used to generate explanatory captions for a range of graphics from a data set about real estate transactions in Pittsburgh.
BibTeX
@conference{Mittal-1995-16198,author = {Vibhu Mittal and Steven F. Roth and Johanna Moore and Joseph Mattis and Giuseppe Carenini},
title = {Generating Explanatory Captions for Information Graphics},
booktitle = {Proceedings of 14th International Joint Conference on Artificial Intelligence (IJCAI '95)},
year = {1995},
month = {August},
pages = {1276 - 1283},
}