Send to

Choose Destination
J Biomed Inform. 2004 Dec;37(6):512-26.

Term identification in the biomedical literature.

Author information

Department of Biomedical Informatics, Columbia Genome Center, Columbia University, New York, USA.


Sophisticated information technologies are needed for effective data acquisition and integration from a growing body of the biomedical literature. Successful term identification is key to getting access to the stored literature information, as it is the terms (and their relationships) that convey knowledge across scientific articles. Due to the complexities of a dynamically changing biomedical terminology, term identification has been recognized as the current bottleneck in text mining, and--as a consequence--has become an important research topic both in natural language processing and biomedical communities. This article overviews state-of-the-art approaches in term identification. The process of identifying terms is analysed through three steps: term recognition, term classification, and term mapping. For each step, main approaches and general trends, along with the major problems, are discussed. By assessing previous work in context of the overall term identification process, the review also tries to delineate needs for future work in the field.

[Indexed for MEDLINE]
Free full text

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center