CAiSE’13

Short-bio

Henning Agt is a PhD student at TU Berlin in the Database Systems and Information Management Group (DIMA). His research focuses on building knowledge-based systems in order to support domain modeling. He works on information extraction from text and ontologies to provide automated modeling suggestions.

Abstract

In order to support the domain modeling process in model-based software development, we automatically create large networks of semantically related terms from natural language. Using part-of-speech tagging, lexical patterns and co-occurrence analysis, and several semantic improvement algorithms, we construct SemNet, a network of approximately 2.7 million single and multi-word terms and 37 million relations denoting the degree of semantic relatedness. This paper gives a comprehensive description of the construction of SemNet, provides examples of the analysis process and compares it to other knowledge bases. We demonstrate the application of the network within the Eclipse/Ecore modeling tools by adding semantically enhanced class name autocompletion and other semantic support facilities like concept similarity.