Aggregating UMLS Semantic Types for Reducing Conceptual Complexity
By Alexa T. McCray, Anita Burgun-Parenthoine, Olivier Bodenreider. Medinfo, 2001
307 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Management Information Systems, Software
View Paper: https://www.semanticscholar.org/paper/426fcd86883e0fb0df2b657b5322afbf6d6539d3
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Josh Tenenbaum
- T. Griffiths
- Charles Kemp
- Dina Demner-Fushman
- Jimmy J. Lin
- François-Michel Lang
- Thomas C. Rindflesch
- J. Urgen Schmidhuber
In Management Information Systems
In Software
Citations in the corpus
- EliXR: an approach to eligibility criteria extraction and representation (2011, methodology): “23 To simplify this network, we manually aggregated nodes that had the same semantic relation with a shared node.”
- Extracting Semantic Predications from Medline Citations for Pharmacogenomics (2006, background): “Semantic Types: Semantic groups have been defined to organize the finer grained UMLS semantic types into broader semantic categories relevant to the clinical domain [25].”
- The interaction of domain knowledge and linguistic structure in natural language processing: interpreting hypernymic propositions in biomedical text (2003, background): “(cid:2) (47) Melatonin is a hormone and antioxidant produced by the pineal gland . . .”
- Answering Clinical Questions with Knowledge-Based and Statistical Techniques (2007, background): “Many of our algorithms operate at the level of coarser-grained semantic types called Semantic Groups (McCray et al., 2001), which capture higher-level generalizations about entities (e.”
- Learning Systems of Concepts with an Infinite Relational Model (2006, methodology): “We assessed the quality of the concept clusters using a 15 cluster partition created by domain experts (McCray et al. 2001).”
- Unsupervised biomedical named entity recognition: Experiments with clinical and biological texts (2013, methodology): “In order to make the method general and portable, classes of entities are defined by users by choosing the corresponding UMLS semantic types, semantic groups [58], or specific concepts which best represent the semantic domains of the classes.”