Semantic Classification of Biomedical Concepts Using Distributional Similarity

@article{citeulike:1607085, abstract = {Objective To develop an automated, high-throughput, and reproducible method for reclassifying and validating ontological concepts for natural language processing applications.Design We developed a distributional similarity approach to classify the Unified Medical Language System (UMLS) concepts. Classification models were built for seven broad biomedically relevant semantic classes created by grouping subsets of the UMLS semantic types. We used contextual features based on syntactic properties obtained from two different large corpora and used [alpha]-skew divergence as the similarity measure.Measurements The testing sets were automatically generated based on the changes by the National Library of Medicine to the semantic classification of concepts from the UMLS 2005AA to the 2006AA release. Error rates were calculated and a misclassification analysis was performed.Results The estimated lowest error rates were 0.198 and 0.116 when considering the correct classification to be covered by our top prediction and top 2 predictions, respectively.Conclusion The results demonstrated that the distributional similarity approach can recommend high level semantic classification suitable for use in natural language processing.}, author = {Fan, Jung-Wei and Friedman, Carol }, citeulike-article-id = {1607085}, doi = {10.1197/jamia.M2314}, journal = {Journal of the American Medical Informatics Association}, keywords = {classification, nlp}, month = {}, number = {4}, pages = {467--477}, posted-at = {2008-06-26 03:48:34}, priority = {2}, title = {Semantic Classification of Biomedical Concepts Using Distributional Similarity}, url = {http://dx.doi.org/10.1197/jamia.M2314}, volume = {14}, year = {2007} }

TY - JOUR ID - citeulike:1607085 L3 - citeulike-article-id:1607085 TI - Semantic Classification of Biomedical Concepts Using Distributional Similarity JF - Journal of the American Medical Informatics Association VL - 14 IS - 4 SP - 467 EP - 477 N2 - Objective To develop an automated, high-throughput, and reproducible method for reclassifying and validating ontological concepts for natural language processing applications.Design We developed a distributional similarity approach to classify the Unified Medical Language System (UMLS) concepts. Classification models were built for seven broad biomedically relevant semantic classes created by grouping subsets of the UMLS semantic types. We used contextual features based on syntactic properties obtained from two different large corpora and used [alpha]-skew divergence as the similarity measure.Measurements The testing sets were automatically generated based on the changes by the National Library of Medicine to the semantic classification of concepts from the UMLS 2005AA to the 2006AA release. Error rates were calculated and a misclassification analysis was performed.Results The estimated lowest error rates were 0.198 and 0.116 when considering the correct classification to be covered by our top prediction and top 2 predictions, respectively.Conclusion The results demonstrated that the distributional similarity approach can recommend high level semantic classification suitable for use in natural language processing. KW - classification KW - nlp AU - Fan, Jung-Wei AU - Friedman, Carol PY - 2007/0// UR - http://dx.doi.org/10.1197/jamia.M2314 ER -