Applications of Natural Language Processing in Biodiversity Science英文文献资料.docVIP

HindawiPublishingCorporation AdvancesinBioinformatics Volume2012,ArticleID391574,17pages doi:10.1155/2012/391574 ReviewArticle ApplicationsofNaturalLanguageProcessingin BiodiversityScience AnneE.Thessen, HongCui, andDmitryMozzherin 1 2 1 1 2 CenterforLibraryandInformatics,MarineBiologicalLaboratory,7MBLStreet,WoodsHole,MA02543,USA SchoolofInformationResourcesandLibraryScience,UniversityofArizona,Tucson,AZ85719,USA CorrespondenceshouldbeaddressedtoAnneE.Thessen,athessen@ Received4November2011;Accepted15February2012 AcademicEditor:J¨orgHakenberg Copyright?2012AnneE.Thessenetal. This is an open access article distributed under the Creative Commons Attribution License,whichpermitsunrestricteduse,distribution,andreproductioninanymedium,providedtheoriginalworkisproperly cited. Centuriesofbiologicalknowledgearecontainedinthemassivebodyofscienti?cliterature,writtenforhuman-readabilitybuttoo bigforanyonepersontoconsume.Large-scaleminingofinformationfromtheliteratureisnecessaryifbiologyistotransform intoadata-drivenscience.Acomputercanhandlethevolumebutcannotmakesenseofthelanguage.Thispaperreviewsand discussestheuseofnaturallanguageprocessing(NLP)andmachine-learningalgorithmstoextractinformationfromsystematic literature.NLPalgorithmshavebeenusedfordecades,butrequirespecialdevelopmentforapplicationinthebiologicalrealmdue tothespecialnatureofthelanguage.Manytoolsexistforbiologicalinformationextraction(cellularprocesses,taxonomicnames, andmorphologicalcharacters),butnonehavebeenappliedlifewideandmoststillrequiretestinganddevelopment.Progresshas beenmadeindevelopingalgorithmsforautomatedannotationoftaxonomictext,identi?cationoftaxonomicnamesintext,and extractionofmorphologicalcharacterinformationfromtaxonomicdescriptions.Thismanuscriptwillbrie?ydiscussthekeysteps inapplyinginformationextractiontoolstoenhancebiodiversityscience. 1.Introduction cyberinfrastructure, data must be ready to enter a digital data pool. This means data must be digita