Spelling suggestions: "subject:"ontologybased information extraction"" "subject:"ontology_based information extraction""
1 |
L’acquisition et l’extraction de connaissances dans un contexte patrimoniale peu documenté / Knowledge acquisition and extraction in the context of poorly documented cultural heritageAmad, Ashraf 06 December 2017 (has links)
L’importance de la documentation du patrimoine culturel croit parallèlement aux risques auxquels il est exposé tels que les guerres, le développement urbain incontrôlé, les catastrophes naturelles, la négligence et les techniques ou stratégies de conservation inappropriées. De plus, la documentation constitue un outil fondamental pour l'évaluation, la conservation, le suivi et la gestion du patrimoine culturel. Dès lors, cet outil majeur nous permet d’estimer la valeur historique, scientifique, sociale et économique de ce patrimoine. Selon plusieurs institutions internationales dédiées à la conservation du patrimoine culturel, il y a un besoin réel de développer et d’adapter de solutions informatiques capables de faciliter et de soutenir la documentation du patrimoine culturel peu documenté surtout dans les pays en développement où il y a un manque flagrant de ressources. Parmi ces pays, la Palestine représente un cas d’étude pertinent dans cette problématique de carence en documentation de son patrimoine. Pour répondre à cette problématique, nous proposons une approche d’acquisition et d’extraction de connaissances patrimoniales dans un contexte peu documenté. Nous prenons comme cas d’étude l’église de la Nativité en Palestine et nous mettons en place notre approche théorique par le développement d’une plateforme d’acquisition et d’extraction de connaissances patrimoniales à l’aide d’un Framework pour la documentation de patrimoine culturel.Notre solution est basée sur les technologies sémantiques, ce qui nous donne la possibilité, dès le début, de fournir une description ontologique riche, une meilleure structuration de l'information, un niveau élevé d'interopérabilité et un meilleur traitement automatique (lisibilité par les machines) sans efforts additionnels.De plus, notre approche est évolutive et réciproque car l’acquisition de connaissance (sous forme structurée) améliore l’extraction de connaissances patrimoniales à partir de texte non structuré et vice versa. Dès lors, l’interaction entre les deux composants de notre système ainsi que les connaissances patrimoniales se développent et s’améliorent au fil de temps surtout que notre système utilise les contributions manuelles et validations des résultats automatiques (dans les deux composants) par les experts afin d’optimiser sa performance. / The importance of cultural heritage documentation increases in parallel with the risks to which it is exposed, such as wars, uncontrolled urban development, natural disasters, neglect and inappropriate conservation techniques or strategies. In addition, this documentation is a fundamental tool for the assessment, the conservation, and the management of cultural heritage. Consequently, this tool allows us to estimate the historical, scientific, social and economic value of this heritage. According to several international institutions dedicated to the preservation of cultural heritage, there is an urgent need to develop computer solutions to facilitate and support the documentation of poorly documented cultural heritage especially in developing countries where there is a lack of resources. Among these countries, Palestine represents a relevant case study in this issue of lack of documentation of its heritage. To address this issue, we propose an approach of knowledge acquisition and extraction in the context of poorly documented heritage. We take as a case study the church of the Nativity in Palestine and we put in place our theoretical approach by the development of a platform for the acquisition and extraction of heritage knowledge. Our solution is based on the semantic technologies, which gives us the possibility, from the beginning, to provide a rich ontological description, a better structuring of the information, a high level of interoperability and a better automatic processing without additional efforts.Additionally, our approach is evolutionary and reciprocal because the acquisition of knowledge (in structured form) improves the extraction of heritage knowledge from unstructured text and vice versa. Therefore, the interaction between the two components of our system as well as the heritage knowledge develop and improve over time especially that our system uses manual contributions and validations of the automatic results (in both components) by the experts to optimize its performance.
|
2 |
Anotação semântica baseada em ontologia: um estudo do português brasileiro em documentos históricos do final do século XIXPereira, Juliana Wolf 01 July 2014 (has links)
Made available in DSpace on 2016-06-02T19:06:12Z (GMT). No. of bitstreams: 1
5898.pdf: 11774674 bytes, checksum: 3cc87530008d9b42c105781f8a1068a3 (MD5)
Previous issue date: 2014-07-01 / Financiadora de Estudos e Projetos / This dissertation presents an approach to proceed with semantic annotation in historical documents from the 19th century that discuss the constitution of the mother tongue, the Portuguese Language in Brazil. The objective is to generate a group of semantically annotated documents in agreement with a domain ontology. To provide this domain ontology, the IntrumentoLinguistico Ontology was built, and it supported the process of automatic semantic annotation. The results obtained with the annotation were analyzed in comparison with the Gold Standard and they presented an elevated level of coincidence, between 0.86 and 1.00 for the Fl-score measure. Besides that, it was possible to locate new documents about the discussed domain in a sample of the Revistas Brazileiras. These results prove the efficacy of the approach of automatic semantic annotation. / Esta dissertação apresenta uma abordagem de anotação semântica automática em documentos históricos do século XIX que discutem a constituição da língua pátria, a Língua Portuguesa no Brasil. O objetivo e gerar um conjunto de documentos semanticamente anotados em acordo com uma ontologia de domínio. Para prover essa ontologia de domínio, foi construída a Ontologia Instrumento Linguístico que apoiou o processo para a realização da anotação semântica automática. Os resultados obtidos com a anotação foram analisados em comparação com o Gold Standard e apresentaram alto grau de coincidência, entre 0.86 e 1.00 para a medida F1-Score. Além disso, foi possível localizar novos documentos sobre o domínio discutido em uma amostra das Revistas Brazileiras. Esses resultados comprovam a eficácia da abordagem de anotação semântica automática.
|
Page generated in 0.181 seconds