An empirical evaluation of ontology-based semantic annotators

The third phase of web means semantic web requires many web pages which are annotated with metadata. Thus, a crucial question is where to acquire these metadata. In this paper we propose our approach, a semi-automatic method to annotate the texts of documents and web pages and employs with a quite comprehensive knowledge base to categorize instances with regard to ontology. The approach is evaluated against the manual annotations and one of the most popular annotation tools which works the same as our tool. The approach is implemented in .net framework and uses the WordNet for knowledge base, an annotation tool for the Semantic Web.

2006

Annotations of Web resources can be created using traditional document annotation tools or more recent approaches such as semantic wikis, semantic blogs and collaborative tagging. Currently no unified model exists for all these different kinds of annotations, making it difficult both to compare and assess annotation tools and to integrate the various kinds of annotation data. We analyse annotations in various domains and present a unified formal model for semantic annotations. We evaluate existing annotation tools from these different domains and show how to map the data these tools produce onto our formal model, thus allowing to access and represent this data in a unified way.

IGI Global eBooks, 2009

This chapter deals with issues related to semantic annotation and ontology population within the framework defined by the Semantic Web (SW). The vision of the Semantic Web, initiated in 1998 by Sir Tim Berners-Lee, aims to structure the information available on the Web. To achieve that goal, the resources, textual or multimedia, must be semantically tagged by metadata so that software agents can utilize them. The idea developed in this chapter is to combine the information extraction (IE) tools with knowledge representation tools from the SW for the achievement of the 2 parallel tasks of semantic annotation and ontology population. The goal is to extract relevant information from the resources based on an ontology, then to populate that ontology with new instances according to the extracted information, and finally to use those instances to semantically annotate the resource. Despite all integration efforts, there is currently a gap between the representation formats of the linguistic tools used to extract information and those of the knowledge representation tools used to model the ontology and store the instances or the semantic annotations. The stake consists in proposing a methodological reflexion on the interoperability of these technologies as well as designing operational solutions for companies and, on a broader scale, for the Web.

International Journal of Internet Technology and Secured Transactions, 2014

The annotation of a web page allows us to associate a semantic to the content of this page. But with the great mass of pages managed through the world, and especially with the advent of the web, their manual annotation is not feasible. In this paper, we will focus on the semiautomatic annotation of the web pages. We will propose an approach and a component (entitled 'Querying Web') for semantic annotation of web pages. The proposal of this component aims at improving the interrogation process in the semantic web environment. Our solution is an enhancement of the first result of annotation done by the 'Semantic Radar' plug-in on the web resources, by new annotations using an enriched domain ontology. Finally, we will present in this paper an evaluation of the automation made by our component.

2004

Following the road in-between purely linguistic annotation and solely ontology-based annotations for the Semantic Web, a hybrid (ontological and linguistic) model and platform, called OntoTag, has been created, aiming at better machine communication, interoperability and language understanding. These capabilities, which are the main topic of this paper, are derived from the incorporation into the platform of a set of linguistic ontologies, which are also the main referent for the generation of multi-levelled and standardized annotations of Semantic Web documents within OntoTag.

International Journal of Computer Applications Technology and Research, 2013

Given that semantic Web realization is based on the critical mass of metadata accessibility and the representation of data with formal knowledge, it needs to generate metadata that is specific, easy to understand and well-defined. However, semantic annotation of the web documents is the successful way to make the Semantic Web vision a reality. This paper introduces the Semantic Web and its vision (stack layers) with regard to some concept definitions that helps the understanding of semantic annotation. Additionally, this paper introduces the semantic annotation categories, tools, domains and models.

2010

The paper compares two semantic annotation frameworks that are designed for unstructured and ungrammatical domains. Both frameworks, namely ontoX (ontology-driven information Extraction) and BNOSA (Bayesian network and ontology based semantic annotation), extensively use ontologies during knowledge building, rule generation and data extraction phases. Both of them claim to be scalable as they allow a knowledge engineer, using either of these frameworks, to employ them for any other domain by simply plugging the corresponding ontology to the framework. They, however, differ in the ways conflicts are resolved and missing values are predicted. OntoX uses two heuristic measures, named level of evidence and level of confidence, for conflict resolution while the same task is performed by BNOSA with the aid of Bayesian networks. BNOSA also uses Bayesian networks to predict missing values. The paper compares the performance of both BNOSA and ontoX on the same data set and analyzes their strengths and weaknesses.

Intelligent Systems in Accounting, Finance and Management, 2015

In this paper we propose a flexible approach that supports heterogeneous requirements on systems for the semantic annotation of web content. The flexibility of the approach originates from a model based on the definition of abstract events, which captures at the logical level the main interactions occurring in a system for combined management of ontologies and web content. Application-specific semantics is then provided operationally as an assignment of handlers to these events. While the abstract events are rather coarse-grained to reduce prior commitment, preconditions on the handlers express application-specific distinctions based on contextual information associated with each specific event. Although the possibility to define completely new handlers guarantees the generality of our approach, we foster convention over configuration by providing a set of default handlers, which can be customized by filling their extension points. The use of customizable handlers, whether or not the default ones, reduces the development effort and guarantees consistent user experience despite evolving requirements. A comprehensive framework for semantic annotation of web content has been realized and will be hereafter introduced.

2013

Studies on Semantic Annotation reveal how trying to match heterogeneous requirements leads to divergent methodologies, models and processes for annotation management and exchange. Community efforts towards the development of shared solutions are important to reduce the "entropy" of the field; nonetheless, any agreement on the ultimate annotation system is unlikely to be achieved. We propose a solution to this problem by defining a comprehensive framework, unbound to any specific design/annotation model, and instantiable into concrete system implementations, to meet different requirements. Towards this goal, we commit to fairly general assumptions, valid across disparate systems and not excessively constraining. Firstly, most systems deal with combined management of ontologies and Web content. Secondly, these systems can be described through a common behavioural model, in terms of an assignment of handlers to predetermined events. This behavioural model can be then enriched...

Knowledge and Information Systems, 2011

Semantic Annotation is required to add machine-readable content to natural language text. A global initiative such as the Semantic Web directly depends on the annotation of massive amounts of textual Web resources. However, considering the amount of those resources, a manual semantic annotation of their contents is neither feasible nor scalable. In this paper we introduce a methodology to partially annotate textual content of Web resources in an automatic and unsupervised way. It uses several well-established learning techniques and heuristics to discover relevant entities in text and to associate them to classes of an input ontology by means of linguistic patterns. It also relies on the Web information distribution to assess the degree of semantic co-relation between entities and classes of the input domain ontology. Special efforts have been put in minimizing the amount of Web accesses required to evaluate entities in order to ensure the scalability of the approach. A manual evaluation has been carried out to test the methodology for several domains showing promising results.