You are here

Semantic Knowledge Representation

Diagram of semantic relationships
Project information
Research Area: 
Researchers: 

Note: this web page will be archived on or around October 1 2019 and will be part of the NLM Lister Hill National Center for Biomedical Communications archive collection.

Semantic Knowledge Representation

In support of innovative information management applications in biomedicine as well as basic research, the Semantic Knowledge Representation project (SKR) efforts use symbolic natural language processing based on the UMLS knowledge sources. SKR research examples include developing and applying the literature-based discovery paradigm using semantic predications. One such project looked into the physiology of sleep and associated pathologies, such as declining sleep quality in aging men, restless legs syndrome, and obstructive sleep apnea; another project exploited predications and graph theory for automatic summarization of biomedical text.

SemRep

A core SKR resource is the SemRep program, which extracts semantic predications from text. Originally developed for biomedical research, SemRep was subsequently extended to genetic etiology and pharmacogenomics. Then, through a general methodology based on ontology and thesauri development, SemRep's application was extended to other fields, such as influenza epidemic preparedness and health promotion.  By applying natural language processing techniques, our research can better inform patients, health care providers, researchers, and the general public.

SemMedDB

The SKR project maintains SemMedDB, a repository of 96.3 million SemRep predications (subject-predicate-object triples) extracted our semantic interpreter SemRep from all MEDLINE citations up to Dec. 2018. This database supports the Semantic MEDLINE web application (SemMed), which integrates PubMed searching, SemRep predications, automatic summarization, and data visualization. The application is intended to help users manage the results of PubMed searches. Output is visualized as an informative graph with links to the original MEDLINE citations.

Downloads related to SemRep, SemMedDB, and SKR are available from our Access to SemRep/SemMedDB/SKR Resources page.

Publications/Tools: 
Libbus B, Rindflesch TC. NLP-Based Information Extraction for Managing the Molecular Biology Literature Proc AMIA Symp. 2002:445-9.
Rindflesch TC, Bean CA, Sneiderman CA. Argument Identification for Arterial Branching Predications Asserted in Cardiac Catheterization Reports Proc AMIA Symp. 2000:704-8.
Rindflesch TC, Tanabe L, Weinstein JN, Hunter L. EDGAR: extraction of drugs, genes and relations from the biomedical literature. Pac Symp Biocomput. 2000:517-28.

Pages