Paper: Enhancing Medical Named Entity Recognition with Features Derived from Unsupervised Methods

ACL ID E14-3003
Title Enhancing Medical Named Entity Recognition with Features Derived from Unsupervised Methods
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

A study of the usefulness of features ex- tracted from unsupervised methods is pro- posed. The usefulness of these features will be studied on the task of performing named entity recognition within one clin- ical sub-domain as well as on the task of adapting a named entity recognition model to a new clinical sub-domain. Four named entity types, all very relevant for clini- cal information extraction, will be studied: Disorder, Finding, Pharmaceutical Drug and Body Structure. The named entity recognition will be performed using con- ditional random fields. As unsupervised features, a clustering of the semantic rep- resentation of words obtained from a ran- dom indexing word space will be used.