BibTeX

@inProceedings{kokkinakis-2008-mesh(R)-73973,
	title        = {MeSH® - From a Controlled Vocabulary to a Processable Resource},
	abstract     = {Large repositories of life science data in the form of domain-specific literature, textual databases and other large specialised textual collections (corpora) in electronic form increase on a daily basis to a level beyond the human mind can grasp and interpret. As the volume of data continues to increase, substantial support from new information technologies and computational techniques grounded in the form of the ever increasing applications of the mining paradigm is becoming apparent. These emerging technologies play an increasingly critical role in aiding research productivity, and they provide the means for reducing the workload for information access and decision support and for speeding up and enhancing the knowledge discovery process. In order to accomplish these higher level goals and support the mining approach however, a fundamental and unavoidable starting point is the identification and mapping of terminology from the textual, unstructured data onto biomedical knowledge sources and concept hierarchies. In this paper, we provide a description of the work regarding terminology recognition using the Swedish MeSH® thesaurus and its corresponding English original source. We explain the various transformation and refinement steps applied to the original database tables into a fully-fledged processing oriented annotating resource. Particular attention has been given to a number of these steps in order to automatically map the extensive variability of lexical terms to structured MeSH® nodes. Issues on annotation and coverage are also discussed.
},
	booktitle    = {Proceedings of the 6th Language Resources and Evaluation Conference (LREC)},
	author       = {Kokkinakis, Dimitrios},
	year         = {2008},
}