Sight for visually impaired users: Summarizing information graphics textually

Information graphics (such as bar charts and line graphs) are widely used in articles from popular media. The majority of such graphics are intended to convey a message which is often not repeated in the text of the article. Thus, graphics together with the textual segments contribute to the overall purpose of an article and cannot be ignored. Unfortunately, these valuable knowledge resources aren't readily accessible to everyone. The thesis of this research is that techniques must be developed for providing effective access to information graphics and that we can apply natural language generation technology to provide the message and knowledge that one would gain from viewing graphics (a form of non-linguistic data) via textual descriptions.;In support of this thesis, this dissertation presents an implemented natural language generation system which first provides a brief initial summary that conveys the underlying intended message of an information graphic along with the graphic's significant and salient features, and then generates follow-up responses that provide further information about the graphic upon request. This work is used to enhance an accessibility system to an interactive natural language system in order to enable visually impaired users to gain access to the informational content of graphics that appear in popular media. The textual descriptions generated by this research can also be utilized in a variety of other natural language applications such as multimodal document summarizers and question answering systems.