Summarizing Relationships for Interactive Concept Map Browsers

Abstract

Concept maps are visual summaries, structured as directed graphs: important concepts from a dataset are displayed as vertexes, and edges between vertexes show natural language descriptions of the relationships between the concepts on the map. Thus far, preliminary attempts at automatically creating concept maps have focused on building static summaries. However, in interactive settings, users will need to dynamically investigate particular relationships between pairs of concepts. For instance, a historian using a concept map browser might decide to investigate the relationship between two politicians in a news archive. We present a model which responds to such queries by returning one or more short, importance-ranked, natural language descriptions of the relationship between two requested concepts, for display in a visual interface. Our model is trained on a new public dataset, collected for this task.

Concept Maps, Their Application Types and Methods in Information and Learning Systems

“…6. Interactive concept map [17,30] Handler [31] proposes to apply interactivity to concept maps in a digital learning environment. In particular, it is proposed to provide text explanations for the edges-relationships between concepts in a response to the corresponding user manipulations with the concept map.…”

“…Automation of interactive concept map construction. Much attention is paid to automating of concept map construction [28,31]. Instead, attempts to automatically construct summary maps based on text have limitations and require an additional search for a balance of automatic processing and editing by an expert in order to achieve the optimal didactic adequacy.…”

“…Such functionality significantly expands the possibilities of educational content presentation using concept maps. The annotated description of the edges in [31] is a didactically significant technique that will help users to analyze the concepts in relation to each other. The widespread use of interactive content support the graph structure in our work [17,30] has demonstrated its practical usefulness and confirms the relevance of the development of such functionality in interactive concept maps.…”