Extracting molecular binding relationships from biomedical text
ANLC '00 Proceedings of the sixth conference on Applied natural language processing
A practical part-of-speech tagger
ANLC '92 Proceedings of the third conference on Applied natural language processing
Term extraction + term clustering: an integrated platform for computer-aided terminology
EACL '99 Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics
Journal of Biomedical Informatics
Finding new terminology in very large corpora
Proceedings of the 3rd international conference on Knowledge capture
Enhanced free text access to anatomically-indexed data
BioMed '02 Proceedings of the ACL-02 workshop on Natural language processing in the biomedical domain - Volume 3
Exploring adjectival modification in biomedical discourse across two genres
BioMed '03 Proceedings of the ACL 2003 workshop on Natural language processing in biomedicine - Volume 13
Identifying important concepts from medical documents
Journal of Biomedical Informatics
Paradigmatic modifiability statistics for the extraction of complex multi-word terms
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
BioNLP '09 Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing
Journal of Biomedical Informatics
Improving term extraction with terminological resources
FinTAL'06 Proceedings of the 5th international conference on Advances in Natural Language Processing
Massive biomedical term discovery
DS'05 Proceedings of the 8th international conference on Discovery Science
Hi-index | 0.00 |
Objectives: To automatically extend downwards an existing biomedical terminology using a corpus and both lexical and terminological knowledge. Methods: Adjectival modifiers are removed from terms extracted from the corpus (three million noun phrases extracted from MEDLINE), and demodified terms are searched for in the terminology (UMLS Metathesaurus, restricted to disorders and procedures). A phrase from MEDLINE becomes a candidate term in the Metathesaurus if the following two requirements are met: 1) a demodified term created from this phrase is found in the terminology and 2) the modifiers removed to create the demodified term also modify existing terms from the terminology, for a given semantic category. A manual review of a sample of candidate terms was performed. Results: Out of the 3 million simple phrases randomly extracted from MEDLINE, 125,000 new terms were identified for inclusion in the UMLS. 83% of the 1000 terms reviewed manually were associated with a relevant UMLS concept. Discussion: The limitations of this approach are discussed, as well as adaptation and generalization issues.