Evolution von semantischen Annotationen (ELISA)
Epidemiologie und Medizinische Biometrie/Statistik
Zusammenfassung der Projektergebnisse
ELISA (Evolution of Semantic Annotations) has been a collaborative project between Luxembourg Institute of Science and Technology (LIST) in Luxembourg (PI Cedric Pruski) and Univ. of Leipzig, Germany (PI Erhard Rahm). The project aims at the development and evaluation of new methods for creating and maintaining semantic annotations. The main focus has been on annotations for medical forms by concepts from biomedical Knowledge Organizing Systems (KOS) such as ontologies to improve the usability of such forms and facilitate interoperability. In many cases, KOS elements serve to annotate information in order to make their semantics explicit for machines, which facilitate the automatic treatment, and in particular, the retrieval of the annotated information. The developed automatic approaches allow the development of semi-automatic annotation processes where the new methods recommend annotations for verification by a medical expert to ensure high annotation quality. Research progress and new insights result in continuous changes of ontologies and KOS so that existing annotations using concepts from a certain KOS version may have to be adapted. ELISA therefore developed methods to detect changes between KOS versions and to identify and adapt affected annotations for different kinds of changes. We also develop cross-lingual annotation methods, e.g., to annotate medical forms in German with concepts from ontologies in English. The latter research has been recognized with a Best Paper Award at the Healthinf 2021 conference.
Projektbezogene Publikationen (Auswahl)
- Annotating medical forms using umls. In International Conference on Data Integration in the Life Sciences, pages 55–69. Springer, 2015
Victor Christen, Anika Groß, Julian Varghese, Martin Dugas, and Erhard Rahm
(Siehe online unter https://doi.org/10.1007/978-3-319-21843-4_5) - A reuse-based annotation approach for medical documents. In International Semantic Web Conference, pages 135–150. Springer, 2016
Victor Christen, Anika Groß, and Erhard Rahm
(Siehe online unter https://doi.org/10.1007/978-3-319-46523-4_9) - Evolution of biomedie cal ontologies and mappings: overview of recent approaches. Computational and structural biotechnology journal, 14:333–340, 2016
Anika Groß, Cédric Pruski, and Erhard Rahm
(Siehe online unter https://doi.org/10.1016/j.csbj.2016.08.002) - Leveraging the impact of ontology evolution on semantic annotations. In European Knowledge Acquisition Workshop, pages 68–82. Springer, 2016
Silvio Domingos Cardoso, Cédric Pruski, Marcos Da Silveira, Ying Chi Lin, Anika Groß, Erhard Rahm, and Chantal Reynaud-Delaître
(Siehe online unter https://doi.org/10.1007/978-3-319-49004-5_5) - Evaluating and improving annotation tools for medical forms. In International Conference on Data Integration in the Life Sciences, pages 1–16. Springer, 2017
Ying-Chi Lin, Victor Christen, Anika Groß, Silvio Domingos Cardoso, Cédric Pruski, Marcos Da Silveira, and Erhard Rahm
(Siehe online unter https://doi.org/10.1007/978-3-319-69751-2_1) - Towards a multi-level approach for the maintenance of semantic annotations. In HEALTHINF, pages 401–406, 2017
Silvio Domingos Cardoso, Chantal Reynaud-Delaître, Marcos Da Silveira, Ying-Chi Lin, Anika Groß, Erhard Rahm, and Cédric Pruski
(Siehe online unter https://doi.org/10.5220/0006230104010406) - A learningbased approach to combine medical annotation results. In International Conference on Data Integration in the Life Sciences, pages 135– 143. Springer, 2018
Victor Christen, Ying-Chi Lin, Anika Groß, Silvio Domingos Cardoso, Cédric Pruski, Marcos Da Silveira, and Erhard Rahm
(Siehe online unter https://doi.org/10.1007/978-3-030-06016-9_13) - Evaluating cross-lingual semantic annotation for medical forms. In HEALTHINF, pages 145–155, 2020
Ying-Chi Lin, Victor Christen, Anika Groß, Toralf Kirsten, Silvio Domingos Cardoso, Cédric Pruski, Marcos Da Silveira, and Erhard Rahm
(Siehe online unter https://doi.org/10.5220/0008979901450155) - Enhancing cross-lingual semantic annotations using deep network sentence embeddings. In HEALTHINF, pages 188–199, 2021 (Best Paper Award)
Ying-Chi Lin, Phillip Hoffmann, and Erhard Rahm
(Siehe online unter https://doi.org/10.5220/0010256801880199)
