Enhancing Clinical Concept Extraction with Contextual Embeddings

22 Feb 2019Yuqi SiJingqi WangHua XuKirk Roberts

Neural network-based representations ("embeddings") have dramatically advanced natural language processing (NLP) tasks, including clinical NLP tasks such as concept extraction. Recently, however, more advanced embedding methods and representations (e.g., ELMo, BERT) have further pushed the state-of-the-art in NLP, yet there are no common best practices for how to integrate these representations into clinical tasks... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Clinical Concept Extraction 2010 i2b2/VA BERTlarge (MIMIC) Exact Span F1 90.25 # 1

Methods used in the Paper