Framework for Semi Automatically Generating Topic Maps

International Workshop: Balancing Ecosystem Values – Innovative Experiments for Sustainable Forestry

Lóránd Kásler ; Zsolt Venczel ; László Zsolt Varga

Others  :  http://CEUR-WS.org/Vol-205/paper7.pdf
PID  :  504

来源: CEUR

【 摘 要 】

The amount of electronically stored textual information is continuously increasing both on the internet and incompany assets, and there are no good solutions to easily locate themost needed information. Because search engines do not take intoaccount the meaning of the word and its context, in the end the userhas to select the right information from the unstructured result set.If the text is annotated and linked to the ontology of the annotation,then the user can directly navigate along the links of the semanticannotation to the desired information.In this paper we present a software framework to semiautomatically generate a semantic representation of the knowledgeof the Networkshop conference series and display on a web portalthe generated ontology together with the references to theoccurrences of the instances in the source text. The frameworkpresented in this paper makes advances in the following fields: wedo not assume that the source text has uniform and formallydefined structure, we address English and Hungarian text as well,we incorporate machine learning techniques in the process, andprovide a flexible content management system for the presentation of the generated Topic Map on a web based portal.