11 Papers
23 Citations
Zhiguo Yu is an academic researcher from University of Texas Health Science Center at Houston. The author has contributed to research in topics: Computer science & Topic model. The author has an hindex of 4, co-authored 9 publications. Previous affiliations of Zhiguo Yu include University of Kentucky & University of Texas at Austin.
Chat about Author
Papers
Retrofitting Word Vectors of MeSH Terms to Improve Semantic Similarity Measures
Zhiguo Yu,Trevor Cohen,Byron C. Wallace,Elmer V. Bernstam,Todd R. Johnson +4 more
- 01 Nov 2016
TL;DR: The experimental results demonstrate that the retrofitted word vector measures obtain a higher correlation with physician judgments and a clear improvement on the correlation with experts’ ratings from the retrofit vector representation in comparison to the vector representation without retrofitting.
42
•Journal Article
Retrofitting Concept Vector Representations of Medical Concepts to Improve Estimates of Semantic Similarity and Relatedness.
TL;DR: In this article, a method that retrofits distributional context vector representations of biomedical concepts using structural information from the UMLS Metathesaurus, such that the similarity between vector representation of linked concepts is augmented.
20
Phrase Based Topic Modeling for Semantic Information Processing in Biomedicine
Zhiguo Yu,Todd R. Johnson,Ramakanth Kavuluru +2 more
- 04 Dec 2013
TL;DR: This paper presents an alternative phrase based LDA model to move from a bag of words or n-grams paradigm to a "bag-of-key-phrases" setting by applying a key phrase extraction technique, the C-value method, to further explore latent themes.
•Posted Content
Retrofitting Concept Vector Representations of Medical Concepts to Improve Estimates of Semantic Similarity and Relatedness
TL;DR: In this article, a method that retrofits distributional context vector representations of biomedical concepts using structural information from the UMLS Metathesaurus is presented, such that the similarity between vector representation of linked concepts is augmented.
11
•Proceedings Article
Initializing and Growing a Database of Health Information Technology (HIT) Events by Using TF-IDF and Biterm Topic Modeling.
Hong Kang,Zhiguo Yu,Yang Gong +2 more
- 01 Jan 2017
TL;DR: This work proposed a novel identification strategy composed of a structured data-based filter and an unstructured data- based classifier using both TF-IDF and biterm topic that holds promise of initializing and growing an HIT database to meet the challenges of collecting, analyzing, sharing, and learning from HIT events at an aggregated level.
8