A Semantic-Based Approach to Building Auxiliary System for Screen-Based Reading

摘要

With an increasing amount of electronic documents,screen-based reading becomes popular, how toimprove the ability of reading deeply and sustaining aprolonged engagement in reading is one of challenges in a digital environment. In this paper, we describe a semantic analysis framework for proactively decreasing fragmented time while screen-based reading. The central idea is to utilize semantic analysis programs to extract an extensive set of information that describes keyword spotting. And the auxiliary knowledge can be used for deeply reading. We discuss the strengths of our semantic analysis programs, namely, text extraction, name recognition, feature matching and knowledge map analysis. We report our results of applying these programs to parse scientific literature, such as citation recognition, the author name recognition, reference extraction and etc. The experimental results show that proposed approach can greatly decrease the fragmented time while reading in the digital environment.