Paper: Investigation of Unsupervised Pattern Learning Techniques for Bootstrap Construction of a Medical Treatment Lexicon

ACL ID W09-1308
Title Investigation of Unsupervised Pattern Learning Techniques for Bootstrap Construction of a Medical Treatment Lexicon
Venue Workshop on Biomedical Natural Language Processing
Session
Year 2009
Authors

Dictionaries of biomedical concepts (e.g. dis- eases, medical treatments) are critical source of background knowledge for systems doing biomedical information retrieval, extraction, and automated discovery. However, the rapid pace of biomedical research and the lack of constraints on usage ensure that such dictio- naries are incomplete. Focusing on medical treatment concepts (e.g. drugs, medical pro- cedures and medical devices), we have devel- oped an unsupervised, iterative pattern learn- ing approach for constructing a comprehen- sive dictionary of medical treatment terms from randomized clinical trial (RCT) ab- stracts. We have investigated different meth- ods of seeding, either with a seed pattern or seed instances (terms), and have compared different ranking methods for ranking ex- t...