MedScan, a natural language processing engine for MEDLINE abstracts. Export

@article{citeulike:139802, abstract = {MOTIVATION: The importance of extracting biomedical information from scientific publications is well recognized. A number of information extraction systems for the biomedical domain have been reported, but none of them have become widely used in practical applications. Most proposals to date make rather simplistic assumptions about the syntactic aspect of natural language. There is an urgent need for a system that has broad coverage and performs well in real-text applications. RESULTS: We present a general biomedical domain-oriented NLP engine called MedScan that efficiently processes sentences from MEDLINE abstracts and produces a set of regularized logical structures representing the meaning of each sentence. The engine utilizes a specially developed context-free grammar and lexicon. Preliminary evaluation of the system's performance, accuracy, and coverage exhibited encouraging results. Further approaches for increasing the coverage and reducing parsing ambiguity of the engine, as well as its application for information extraction are discussed.}, address = {Ariadne Genomics, Inc, 9100 Great Seneca HWY, Rockville, MD 20850, USA.}, author = {Novichkova, S. and Egorov, S. and Daraselia, N.}, citeulike-article-id = {139802}, citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/12967967}, citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=12967967}, day = {1}, issn = {1367-4803}, journal = {Bioinformatics}, keywords = {ariadne-genomics, refine}, month = {September}, number = {13}, pages = {1699--1706}, posted-at = {2008-01-10 16:02:22}, priority = {2}, title = {MedScan, a natural language processing engine for MEDLINE abstracts.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/12967967}, volume = {19}, year = {2003} }

TY - JOUR ID - citeulike:139802 L3 - citeulike-article-id:139802 N2 - MOTIVATION: The importance of extracting biomedical information from scientific publications is well recognized. A number of information extraction systems for the biomedical domain have been reported, but none of them have become widely used in practical applications. Most proposals to date make rather simplistic assumptions about the syntactic aspect of natural language. There is an urgent need for a system that has broad coverage and performs well in real-text applications. RESULTS: We present a general biomedical domain-oriented NLP engine called MedScan that efficiently processes sentences from MEDLINE abstracts and produces a set of regularized logical structures representing the meaning of each sentence. The engine utilizes a specially developed context-free grammar and lexicon. Preliminary evaluation of the system's performance, accuracy, and coverage exhibited encouraging results. Further approaches for increasing the coverage and reducing parsing ambiguity of the engine, as well as its application for information extraction are discussed. IS - 13 JF - Bioinformatics SN - 1367-4803 AD - Ariadne Genomics, Inc, 9100 Great Seneca HWY, Rockville, MD 20850, USA. EP - 1706 TI - MedScan, a natural language processing engine for MEDLINE abstracts. VL - 19 SP - 1699 KW - ariadne-genomics KW - refine AU - Novichkova, S AU - Egorov, S AU - Daraselia, N PY - 2003/09/01/ UR - http://view.ncbi.nlm.nih.gov/pubmed/12967967 ER -