Extraction of specific nursing terms using corpora comparison.

The purpose of the study is to develop and evaluate a bottom-up approach to extract the specific nursing terms from textual nursing records using corpora comparison. A nursing records corpus was developed as the target corpus, and a newspaper corpus and a medical literature abstracts corpus were developed as the reference corpora. Two filters were established to extract the technical terms and the relative frequency ratio was used for corpora comparison. The issues related to the improvement of both the algorithms and the evaluation methods were discussed.