The Textual Semantic Lens

Abstract

People often feel the limitation of time to read the continuously increasing articles they need to read. It is a grand challenge to handle the explosion of articles. To understand how humans read articles and get the meaning is the basis of improving the efficiency of reading articles. The underlying semantic links between language units of different granularities reflect some basic semantics. Sentence is the basic language unit for accurately indicating semantics. By defining concepts and the dependent set of sentences, and constructing the semantic link network of dependent sentences and semantic link network of concepts, this paper proposes the textual semantic lens with a set of functions for helping people comprehend articles. Integrating with the semantic link networks of articles, the semantic lens can help people efficiently read large-scale articles.