DMCA
Word sense disambiguation by selecting the best semantic type based on Journal Descriptor Indexing: preliminary experiment (2006)
| Venue: | J. Am. Soc. Inform. Sci. Tech |
| Citations: | 20 - 1 self |
BibTeX
@ARTICLE{Humphrey06wordsense,
author = {Susanne M. Humphrey and Willie J. Rogers and Halil Kilicoglu and Dina Demner-fushman and Thomas C. Rindflesch},
title = {Word sense disambiguation by selecting the best semantic type based on Journal Descriptor Indexing: preliminary experiment},
journal = {J. Am. Soc. Inform. Sci. Tech},
year = {2006},
volume = {57},
pages = {96--113}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
An experiment was performed at the National Library of Medicine ® (NLM ® ) in word sense disambiguation (WSD) using the Journal Descriptor Indexing (JDI) methodology. The motivation is the need to solve the ambiguity problem confronting NLM’s MetaMap system, which maps free text to terms corresponding to concepts in NLM’s Unified Medical Language System ® (UMLS ® ) Metathesaurus ®. If the text maps to more than one Metathesaurus concept at the same high confidence score, MetaMap has no way of knowing which concept is the correct mapping. We describe the JDI methodology, which is ultimately based on statistical associations between words in a training set of MEDLINE ® citations and a small set of journal descriptors (assigned by humans to journals per se) assumed to be inherited by the citations. JDI is the
Keyphrases
journal descriptor indexing word sense disambiguation semantic type preliminary experiment metathesaurus concept free text statistical association high confidence score small set ambiguity problem medline citation training set journal descriptor nlm metamap system national library correct mapping jdi methodology nlm unified medical language system
