Paper: Recognizing Medication related Entities in Hospital Discharge Summaries using Support Vector Machine

ACL ID C10-2030
Title Recognizing Medication related Entities in Hospital Discharge Summaries using Support Vector Machine
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

Due to the lack of annotated data sets, there are few studies on machine learning based approaches to extract named enti- ties (NEs) in clinical text. The 2009 i2b2 NLP challenge is a task to extract six types of medication related NEs, includ- ing medication names, dosage, mode, frequency, duration, and reason from hospital discharge summaries. Several machine learning based systems have been developed and showed good per- formance in the challenge. Those systems often involve two steps: 1) recognition of medication related entities; and 2) deter- mination of the relation between a medi- cation name and its modifiers (e.g., do- sage). A few machine learning algo- rithms including Conditional Random Field (CRF) and Maximum Entropy have been applied to the Named Entity Recog- ni...