Evaluating the Semantic Web: A Task-Based Approach

Abstract

Abstract. The increased availability of online knowledge has led to the design of several algorithms that solve a variety of tasks by harvesting the Semantic Web, i.e., by dynamically selecting and exploring a multitude of online ontologies. Our hypothesis is that the performance of such novel algorithms implicitly provides an insight into the quality of the used ontologies and thus opens the way to a task-based evaluation of the Semantic Web. We have investigated this hypothesis by studying the lessons learnt about online ontologies when used to solve three tasks: ontology matching, folksonomy enrichment, and word sense disambiguation. Our analysis leads to a suit of conclusions about the status of the Semantic Web, which highlight a number of strengths and weaknesses of the semantic information available online and complement the findings of other analysis of the Semantic Web landscape.

Maintenance of Human and Machine Metadata over the Web Content

“…As the result of this complication only a small part of the Web is covered by ontologies [9]. An improvement can be achieved by lightweight ontologies which usually contain only basic elements as terms or concepts and "is-a" and "part-of" relations [10].…”

Semantically enhanced Information Retrieval: An ontology-based approach

“…Their potential to overcome the limitations of keyword-based search in the IR context was soon envisaged, and was explored by several researchers in the SW area (Maedche, Staab, Stojanovic, Studer & Sure, 2003;Guha, McCool & Miller, 2003;Kiryakov, Popov, Terziev, Manov & Ognyanoff, 2004). However, these approaches exhibit certain limitations like: a) the still sparseness of the available SW content (Sabou, Gracia, Angeletou, d'Aquin & Motta, 2007), leading to knowledge incompleteness when applying search to heterogeneous sources of information, b) the poor usability of the systems, specially at the level of query, requiring users to manage complex languages or interfaces to express their information needs, c) the lack of ranking algorithms to cope with large-scale information sources, etc (see Section 2.3). One may say that the undertakings in information search and retrieval from the SW community have not yet taken full advantage of the acquired knowledge, accumulated experience, and theoretical and technical achievements developed through several decades of work in the IR field tradition.…”

Utilizing Microblogs for Web Page Relevant Term Acquisition

“…This vision of machine-processable layer of metadata is for more than a decade addressed by the Semantic Web movement [3]. However, despite the increase, "semantization" of the Web is not as spread as we would like [15]. It is due to the fact, that manual creation of metadata for huge amounts of web content is almost impossible for a human being.…”