Artículos regulares

 

Inferring Relations and Annotations in Semantic Network: Application to Radiology

 

Lionel Ramadier^1,2, Manel Zarrouk¹, Mathieu Lafourcade¹, and Antoine Micheau²

 

¹ LIRMM, Montpellier, France. lionel.ramadier@lirmm.fr, manel.zarrouk@lirmm.fr, mathieu.lafourcade@lirmm.fr

² IMAIOS, MIBI, Montpellier, France. antoine.micheau@imaios.com.

 

Article received on 10/01/2014.
Accepted on 01/02/2014.

 

Abstract

Domain-specific ontologies are invaluable despite many challenges associated with their development. In most cases, domain knowledge bases are built with very limited scope without considering the benefits of plunging domain knowledge to a general ontology. Furthermore, most existing resources lack meta-information about association strength (weights) and annotations (frequency information like frequent, rare, etc. or relevance information like pertinent or irrelevant). In this paper, we present a semantic resource for radiology built over an existing general semantic lexical network (JeuxDeMots). This network combines weight and annotations on typed relations between terms and concepts. Some inference mechanisms are applied to the network to improve its quality and coverage. We extend this mechanism to relation annotation. We describe how annotations are handled and how they improve the network by imposing new constraints especially those founded on medical knowledge.

Keywords: Relation inference, lexical semantic network, relation annotation, radiology.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

References

1. Bodenreider, O. (2008). Biomedical ontologies in action: role in knowledge management, data integration and decision support. Yearb Med Inform, 47, 67–79.         [ Links ]

2. Lomax, J. & McCray, A.T. (2004). Mapping the gene ontology into the unified medical language system. Comparative and functional genomics, 5(4), 354–361.         [ Links ]

3. Yetisgen-Yildiz, M., Gunn, M.L., Xia, F., & Payne, T.H. (2013). A text processing pipeline to extract recommendations from radiology reports. Journal of biomedical informatics, (46), 354–362.         [ Links ]

4. Mejino Jr, J.L., Rubin, D.L., & Brinkley, J.F. (2008). FMA-RadLex: An application ontology of radiological anatomy derived from the foundational model of anatomy reference ontology. AMIA Annual Symposium Proceedings, 465, American Medical Informatics Association.

5. Rubin, D.L. (2008). Creating and curating a terminology for radiology: ontology modeling and analysis. Journal of digital imaging, 21(4), 355–362.         [ Links ]

6. Hong, Y., Zhang, J., Heilbrun, M.E., & Kahn Jr, C.E. (2012). Analysis of RadLex coverage and term co-occurrence in radiology reporting templates. Journal of Digital Imaging, 25(1), 56–62.         [ Links ]

7. Gerstmair, A., Daumke, P., Simon, K., Langer, M., & Kotter, E. (2012). Intelligent image retrieval based on radiology reports. European radiology, 22(12), 2750–2758.         [ Links ]

8. Liu, H. & Singh, P. (2004). ConceptNet—a practical commonsense reasoning tool-kit. BT technology journal, 22(4), 211–226.         [ Links ]

9. Lafourcade, M (2007). Making people play for Lexical Acquisition. 7th Symposium on Natural Language Processing (SNLP 2007), Pattaya, Thailande, 8 p.         [ Links ]

10. Zarrouk, M., Lafourcade, M., & Joubert, A. (2013). Inference and Reconciliation in a Crowdsourced Lexical-Semantic Network. Computación y Sistemas, Vol. 17, No. 2, 2013 147–159.         [ Links ]

11. Thaler, S., Siorpaes, K., Simperl, E., & Hofer, C. (2011). A survey on games for knowledge acquisition. Rapport technique, STI, 26 p.         [ Links ]

12. Ramadier, L.M., Zarrouk , Z, Lafourcade , M., & Micheau, A. (2014). Spreading Relation Annotations in a lexical semantic network: Applied to radiology. International Conference on Intelligent Text Processing and Computational Linguistics, CICLing 2014. Lectures Notes in Computer Science, Vol. 8403, 40–51.         [ Links ]