N09-2048 to leave , achieves the highest concept identification rates . The differences in concept
D15-1069 also developed learning-based key concept identification to build queries from EHR notes
D15-1069 Concept Identification The key concept identification performance of the three CRF
C94-1059 . Concepts are represented by concept identification numbers ( To distinguish concepts
D15-1171 the geometry language Q . The concept identification stage maps words or phrases to
N09-2048 system prompts can lead to higher concept identification rates . 2 Experimental Method
D15-1069 adaptation techniques to learn key concept identification models from other data sources
D15-1069 We explored topic model and key concept identification methods to construct queries
K15-1004 for providing the results of his concept identification . <title> AIDA2 : A Hybrid Approach
J02-4005 syntactic and semantic analysis , concept identification , and text regeneration . Our
K15-1004 POS tags information after the concept identification stage , we use it to recall some
D15-1069 ttest ( p &lt; 0.05 ) . 4.2 Key Concept Identification The key concept identification
D15-1069 future research . Firstly , our key concept identification methods are not optimized for
D15-1069 80 % . 3.2.3 Learning-Based Key Concept Identification We also developed learning-based
K15-1004 constituent parsing . The recall of the concept identification stage from Flanigan et al. (
N09-2048 choices in user responses ; and 2 ) concept identification rates for user responses . We
D15-1069 the same thread . <title> Key Concept Identification for Medical Information Retrieval
C96-2157 However , automating the process of concept identification in untbrmatted text has not been
K15-1004 left side . 4 . We augment the concept identification procedure of Flanigan et al.
D15-1171 satistfied in the formal language . 4.1 Concept Identification Concepts are defined as symbols
hide detail