Designing A Question-Answering System for Comic Contents

The objective of our research is to create a question answering system for comics. Because a comic has multimodal contents, we have to answer questions about text as well as illustrations. This is different from the conventional question answering system. To solve this problem, in this study, we organized the information to be obtained from comic illustrations and examined the framework of question answering for this content. Then, we built a prototype system and examined the question answering system for comic contents.