Abstract
Medical document written in natural language is available in electronic form, and it constitutes an invaluable source for medical research. This paper describes our system based on hybrid approach for the task of Named Entity Recognition and Normalization of French medical documents using QUAERO corpus [1]. To evaluate our system, we took part in three subtasks: Entity Normalization, Named Entity Extraction and Classification which involved 10 categories including Anatomy, Chemicals & Drugs, Devices, Disorders, Geographic Areas, Living Beings, Objects, Phenomena, Physiology and Procedures. The results on both tasks, Named Entity Recognition and Normalization, demonstrate high performance as compared to other methods for French Medical Entity Recognition and Normalization.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
