Feature: text analysis
Jelena M. Jovanović, Ebrahim Bagheri, John Cuzzola, Zoran Jeremić · 2014
I n the last few years, there has been a constant increase in the number and variety of online applications that rely on machine comprehension of human language to offer advanced functionalities, such as semantic search, question answering, and recommendation. These functionalities are often enabled by information extraction services that couple text analysis and machine-learning methods and techniques, with large, general-purpose knowledge bases such as Wikipedia. Information extraction—an active area of text analysis research—has experienced steady growth in recent years.1 The latest developments in data storage and processing, enabled by cloud infrastructure, have synergized many advanced information extraction methods and techniques, so that text can be processed and relevant information extracted almost instantaneously. The significant increase in the efficiency of automated text analysis, coupled with an increase in the overall quality of extracted information, has made information extraction services appealing for a variety of real-world application areas: