Unsupervised approaches for textual semantic annotation, a survey

Abstract

Semantic annotation is a crucial part of achieving the vision of the Semantic Web and has long been a research topic among various communities. The most challenging problem in reaching the Semantic Web's real potential is the gap between a large amount of unlabeled existing/new data and the limited annotation capability available. To resolve this problem, numerous works have been carried out to increase the degree of automation of semantic annotation from manual to semi-automatic to fully automatic. The richness of these works has been well-investigated by numerous surveys focusing on different aspects of the problem. However, a comprehensive survey targeting unsupervised approaches for semantic annotation is still missing and is urgently needed. To better understand the state-of-the-art of semantic annotation in the textual domain adopting unsupervised approaches, this article investigates existing literature and presents a survey to answer three research questions: (1) To what extent can semantic annotation be performed in a fully automatic manner by using an unsupervised way? (2) What kind of unsupervised approaches for semantic annotation already exist in literature? (3) What characteristics and relationships do these approaches have? In contrast to existing surveys, this article helps the reader get an insight into the state-of-art of semantic annotation using unsupervised approaches. While examining the literature, this article also addresses the inconsistency in the terminology used in the literature to describe the various semantic annotation tools' degree of automation and provides more consistent terminology. Based on this, a uniform summary of the degree of automation of the many semantic annotation tools that were previously investigated can now be presented.