Ontology based entity disambiguation with natural language patterns

Kleb, Joachim; Volz, Raphael

doi:10.1109/icdim.2009.5356769

Cited by 7 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach by Volz et al [26] used contextual information for detecting the concept affiliation of entities. Kleb et al [14] used concept-dependant text patterns for the disambiguation of text information. Gruhl et al [9] trained an SVM classifier in order to spot ontology entities.…”

Section: Related Workmentioning

confidence: 99%

“…Thus we had to construct our own evaluation scenario. In order to reflect the ambiguity of ontology elements we used a highly ambiguous geography ontology which is a refinement from [26,14]. It currently contains 132,087,082 RDF(S) triples, including 18 classes, 50 relations, and instance data collected from Geonames.org (information from NGA, GNIS and 36 additional sources 9 ).…”

Section: Ontology and Input Datamentioning

confidence: 99%

“…[26,14]) crawled from the European Media Monitor (EMM [19]) which collects news of European newspapers and clusters them topic-wise. We chose the topic natural disasters in order to guarantee for documents including geographic entities.…”

Section: Ontology and Input Datamentioning

confidence: 99%

“…Also, many try to transfer NLP approaches to this domain [26,14,9], mostly focusing on a specific domain, using domain-specific measures. So far, in the field of ontology-based entity disambiguation, domain-independent complex structures in semantic graphs have not been exploited.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Entity Reference Resolution via Spreading Activation on RDF-Graphs

Kleb

Abecker

2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. The use of natural language identifiers as reference for ontology elements-in addition to the URIs required by the Semantic Web standards-is of utmost importance because of their predominance in the human everyday life, i.e. speech or print media. Depending on the context, different names can be chosen for one and the same element, and the same element can be referenced by different names. Here homonymy and synonymy are the main cause of ambiguity in perceiving which concrete unique ontology element ought to be referenced by a specific natural language identifier describing an entity. We propose a novel method to resolve entity references under the aspect of ambiguity which explores only formal background knowledge represented in RDF graph structures. The key idea of our domain independent approach is to build an entity network with the most likely referenced ontology elements by constructing steiner graphs based on spreading activation. In addition to exploiting complex graph structures, we devise a new ranking technique that characterises the likelihood of entities in this network, i.e. interpretation contexts. Experiments in a highly polysemic domain show the ability of the algorithm to retrieve the correct ontology elements in almost all cases.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Ontology and Input Datamentioning

confidence: 99%

Section: Ontology and Input Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Entity Reference Resolution via Spreading Activation on RDF-Graphs

Kleb

Abecker

2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…We plan to integrate further CTC components into the SUI ontology system. The near-term focus will include components for text-to-query conversion, disambiguation of geo-spatial references [14], reasoning brokerage [3] and integration of growing pools of web data ("Linked Open Data" [10]). …”

Section: Driving the Change -A Comprehensive Ontology Managementmentioning

confidence: 99%

Leveraging Ontologies for Environmental Information Systems

Bügel

Schmieder

Schnebel

et al. 2011

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Abstract. The provision of accurate, comprehensive and condensed information contained in distributed environmental information systems via public search interfaces raises several technological challenges. Our approach to tackle these challenges is based on a consequent use of ontologies. Starting with an analysis of requirements resulting from semantic search scenarios, we explain the advantages of using ontologies based on standards and aim to reuse and transform terminological systems available in the environmental domain into ontologies. We develop an architecture guided by the premise of exerting a minimum of influence on existing search infrastructures. As a consequence of using a (possibly large) number of ontologies, tools for ontology management are needed. A key argument for using ontologies is that nowadays -as an outcome of the Semantic Web initiative -very powerful processing tools are available. We elaborate ontology mapping as an example and outline how a comprehensive ontology management can be achieved.

show abstract