Automatic Caption Generation for Electronics Textbooks

Automatic or semi-automatic approaches for developing Technology Supported Learning Systems (TSLS) are required to lighten their development cost. The main objective of this paper is to automate the generation of a caption module; it aims at reproducing the way teachers prepare their lessons and the learning material they will use throughout the course. Teachers tend to choose one or more textbooks that cover the contents of their subjects, determine the topics to be addressed, and identify the parts of the textbooks which may be helpful for the students it describes the entities, attributes, role and their relationship plus the constraints that govern the problem domain. The caption model is created in order to represent the vocabulary and key concepts of the problem domain. The caption model also identifies the relationships among all the entities within the scope of the problem domain, and commonly identifies their attributes. It defines a vocabulary and is helpful as a communication tool. DOM-Sortze, a framework that enables the semi-automatic generation of the Caption Module for technology supported learning system (TSLS) from electronic textbooks. The semiautomatic generation of the Caption Module entails the identification and elicitation of knowledge from the documents to which end Natural Language Processing (NLP) techniques are combined with ontologies and heuristic reasoning.