Skip to Main content Skip to Navigation
Master Thesis

Modélisation d'une ontologie de domaine et des outils d'extraction de l'information associés pour l'anglais et le français

Abstract : Nowadays, the increasing of information sources (websites, newspapers, radio, TV, etc.) has led to "dig" these documents in order to extract relevant knowledge considering a set purpose. The IPCC team at EADS Defence & Security is responsible for invention in media mining. This thesis introduces a domain ontology and the associated tools for information extraction in English and French texts. After a brief analysis of existing tools and techniques in ontology development and information extraction, we present the work done during our training course. First, we used the Protégé tool to create a small OWL domain ontology dedicated to military intelligence. In order to recognize the elements of interest, we have built, through GATE architecture, a system to extract named entities, events and relations. We present here our methodology, the different stages of implementation as well as a quantitative and qualitative evaluation of our results.
Document type :
Master Thesis
Complete list of metadata

Cited literature [35 references]  Display  Hide  Download

https://dumas.ccsd.cnrs.fr/dumas-00569002
Contributor : Uga - Bulles <>
Submitted on : Thursday, February 24, 2011 - 9:51:12 AM
Last modification on : Sunday, March 14, 2021 - 9:54:03 PM
Long-term archiving on: : Wednesday, May 25, 2011 - 2:43:40 AM

Identifiers

  • HAL Id : dumas-00569002, version 1

Citation

Laurie Serrano. Modélisation d'une ontologie de domaine et des outils d'extraction de l'information associés pour l'anglais et le français. Linguistique. 2010. ⟨dumas-00569002⟩

Share

Metrics

Record views

813

Files downloads

2656