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.
|Advisor:||Carberry, Sandra, McCoy, Kathleen|
|Commitee:||Elzer, Stephanie, Shanker, Vijay|
|School:||University of Delaware|
|Department:||Department of Computer and Information Sciences|
|School Location:||United States -- Delaware|
|Source:||DAI-B 71/11, Dissertation Abstracts International|
|Keywords:||Accessibility, Graph summarization, Information graphics, Natural language generation, Visually impaired users|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be