Automatically generating text to accompany information graphics

Generally, when quantitative information is to be presented, some form of graphical presentation is used, often with a textual caption to ensure that the audience notices certain aspects of the data. Mary Ellen Foster has investigated the principles that a system aiming to produce such captions automatically should follow. The process of caption generation is examined in the context of the standard tasks in text generation. Most previous systems in this area produce textual summaries that are intended to stand alone; the issues involved in producing a caption differ, as the text must be coordinated with the graphic it is to accompany. We have developed CAPUT, a prototype caption-generation system that follows these principles to generate single-sentence captions for information graphics of the type that might appear in a newspaper article.

Reference:

Return to Research by Graeme Hirst and students