Extracting semantic predications from Medline citations for pharmacogenomics.

by: CB Ahlers, M Fiszman, D Demner-Fushman, FM Lang, TC Rindflesch

Pac Symp Biocomput (2007), pp. 209-220.

View FullText article

Pubmed, Hubmed, http://psb.stanford.edu/psb-online/procee…

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

ibuch, Gaetan

Find related articles with these CiteULike tags

medline, pharmacogenomics, textmining

Abstract

We describe a natural language processing system (Enhanced SemRep) to identify core assertions on pharmacogenomics in Medline citations. Extracted information is represented as semantic predications covering a range of relations relevant to this domain. The specific relations addressed by the system provide greater precision than that achievable with methods that rely on entity co-occurrence. The development of Enhanced SemRep is based on the adaptation of an existing system and crucially depends on domain knowledge in the Unified Medical Language System. We provide a preliminary evaluation (55% recall and 73% precision) and discuss the potential of this system in assisting both clinical practice and scientific investigation.

@article{citeulike:2155675, abstract = {We describe a natural language processing system (Enhanced SemRep) to identify core assertions on pharmacogenomics in Medline citations. Extracted information is represented as semantic predications covering a range of relations relevant to this domain. The specific relations addressed by the system provide greater precision than that achievable with methods that rely on entity co-occurrence. The development of Enhanced SemRep is based on the adaptation of an existing system and crucially depends on domain knowledge in the Unified Medical Language System. We provide a preliminary evaluation (55\% recall and 73\% precision) and discuss the potential of this system in assisting both clinical practice and scientific investigation.}, address = {Lister Hill National Center for Biomedical Communications, National Library of Medicine Bethesda, Maryland 20894, USA.}, author = {Ahlers, C. B. and Fiszman, M. and Demner-Fushman, D. and Lang, F. M. and Rindflesch, T. C. }, citeulike-article-id = {2155675}, issn = {1793-5091}, journal = {Pac Symp Biocomput}, keywords = {medline}, pages = {209--220}, posted-at = {2007-12-21 14:22:19}, priority = {2}, title = {Extracting semantic predications from Medline citations for pharmacogenomics.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/17990493}, year = {2007} }

RIS record

TY - JOUR ID - citeulike:2155675 L3 - citeulike-article-id:2155675 TI - Extracting semantic predications from Medline citations for pharmacogenomics. JF - Pac Symp Biocomput SP - 209 EP - 220 AD - Lister Hill National Center for Biomedical Communications, National Library of Medicine Bethesda, Maryland 20894, USA. SN - 1793-5091 N2 - We describe a natural language processing system (Enhanced SemRep) to identify core assertions on pharmacogenomics in Medline citations. Extracted information is represented as semantic predications covering a range of relations relevant to this domain. The specific relations addressed by the system provide greater precision than that achievable with methods that rely on entity co-occurrence. The development of Enhanced SemRep is based on the adaptation of an existing system and crucially depends on domain knowledge in the Unified Medical Language System. We provide a preliminary evaluation (55% recall and 73% precision) and discuss the potential of this system in assisting both clinical practice and scientific investigation. KW - medline AU - Ahlers, CB AU - Fiszman, M AU - Demner-Fushman, D AU - Lang, FM AU - Rindflesch, TC PY - 2007/// UR - http://view.ncbi.nlm.nih.gov/pubmed/17990493 ER -

RIS BibTeX