{"id":"https://openalex.org/W1987248861","doi":"https://doi.org/10.1155/2012/391574","title":"Applications of Natural Language Processing in Biodiversity Science","display_name":"Applications of Natural Language Processing in Biodiversity Science","publication_year":2012,"publication_date":"2012-05-22","ids":{"openalex":"https://openalex.org/W1987248861","doi":"https://doi.org/10.1155/2012/391574","mag":"1987248861","pmid":"https://pubmed.ncbi.nlm.nih.gov/22685456"},"language":"en","primary_location":{"id":"doi:10.1155/2012/391574","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2012/391574","pdf_url":"https://downloads.hindawi.com/archive/2012/391574.pdf","source":{"id":"https://openalex.org/S146125958","display_name":"Advances in Bioinformatics","issn_l":"1687-8027","issn":["1687-8027","1687-8035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://downloads.hindawi.com/archive/2012/391574.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028696519","display_name":"Anne Thessen","orcid":"https://orcid.org/0000-0002-2908-3327"},"institutions":[{"id":"https://openalex.org/I1338920048","display_name":"Marine Biological Laboratory","ror":"https://ror.org/046dg4z72","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1338920048"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anne E. Thessen","raw_affiliation_strings":["Center for Library and Informatics, Marine Biological Laboratory, 7 MBL Street, Woods Hole, MA 02543, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Library and Informatics, Marine Biological Laboratory, 7 MBL Street, Woods Hole, MA 02543, USA","institution_ids":["https://openalex.org/I1338920048"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044387303","display_name":"Hong Cui","orcid":"https://orcid.org/0000-0001-6218-283X"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Cui","raw_affiliation_strings":["School of Information Resources and Library Science, University of Arizona, Tucson, AZ 85719, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Resources and Library Science, University of Arizona, Tucson, AZ 85719, USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082529553","display_name":"Dmitry Mozzherin","orcid":"https://orcid.org/0000-0003-1593-1417"},"institutions":[{"id":"https://openalex.org/I1338920048","display_name":"Marine Biological Laboratory","ror":"https://ror.org/046dg4z72","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1338920048"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitry Mozzherin","raw_affiliation_strings":["Center for Library and Informatics, Marine Biological Laboratory, 7 MBL Street, Woods Hole, MA 02543, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Library and Informatics, Marine Biological Laboratory, 7 MBL Street, Woods Hole, MA 02543, USA","institution_ids":["https://openalex.org/I1338920048"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028696519"],"corresponding_institution_ids":["https://openalex.org/I1338920048"],"apc_list":null,"apc_paid":null,"fwci":1.7466,"has_fulltext":true,"cited_by_count":97,"citation_normalized_percentile":{"value":0.83605254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2012","issue":null,"first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7906104922294617},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.675530731678009},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6385890245437622},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5568100214004517},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.531010091304779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5262707471847534},{"id":"https://openalex.org/keywords/realm","display_name":"Realm","score":0.45337459444999695},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4509415924549103},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4468899965286255},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4452044367790222},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.17562046647071838},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09712812304496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906104922294617},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.675530731678009},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6385890245437622},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5568100214004517},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.531010091304779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5262707471847534},{"id":"https://openalex.org/C2778757428","wikidata":"https://www.wikidata.org/wiki/Q1250464","display_name":"Realm","level":2,"score":0.45337459444999695},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4509415924549103},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4468899965286255},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4452044367790222},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.17562046647071838},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09712812304496765},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1155/2012/391574","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2012/391574","pdf_url":"https://downloads.hindawi.com/archive/2012/391574.pdf","source":{"id":"https://openalex.org/S146125958","display_name":"Advances in Bioinformatics","issn_l":"1687-8027","issn":["1687-8027","1687-8035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:22685456","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22685456","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in bioinformatics","raw_type":null},{"id":"pmh:oai:darchive.mblwhoilibrary.org:1912/5235","is_oa":true,"landing_page_url":"https://hdl.handle.net/1912/5235","pdf_url":null,"source":{"id":"https://openalex.org/S4306400781","display_name":"Open Access Server of the Woods Hole Scientific Community (Woods Hole Scientific Community)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:europepmc.org:2376873","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3364545","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1155/2012/391574","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2012/391574","pdf_url":"https://downloads.hindawi.com/archive/2012/391574.pdf","source":{"id":"https://openalex.org/S146125958","display_name":"Advances in Bioinformatics","issn_l":"1687-8027","issn":["1687-8027","1687-8035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1303921851","display_name":"DataNet Full Proposal: The Data Conservancy (A Digital Research and Curation Virtual Organization)","funder_award_id":"0830976","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G247860501","display_name":"Fine-Grained Semantic Markup of Descriptive Data for Knowledge Applications in Biodiversity Domains","funder_award_id":"0849982","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306142","display_name":"John D. and Catherine T. MacArthur Foundation","ror":"https://ror.org/00dxczh48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1987248861.pdf","grobid_xml":"https://content.openalex.org/works/W1987248861.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W23149702","https://openalex.org/W55629104","https://openalex.org/W90158706","https://openalex.org/W204408055","https://openalex.org/W1486198665","https://openalex.org/W1495210209","https://openalex.org/W1539893811","https://openalex.org/W1548849615","https://openalex.org/W1561585380","https://openalex.org/W1562456900","https://openalex.org/W1591167068","https://openalex.org/W1623698862","https://openalex.org/W1729680593","https://openalex.org/W1796991281","https://openalex.org/W1818857488","https://openalex.org/W1852237973","https://openalex.org/W1907229881","https://openalex.org/W1970835563","https://openalex.org/W1987522618","https://openalex.org/W1994474588","https://openalex.org/W2001306005","https://openalex.org/W2002507929","https://openalex.org/W2007859640","https://openalex.org/W2009264880","https://openalex.org/W2010013632","https://openalex.org/W2014676366","https://openalex.org/W2039511449","https://openalex.org/W2049770399","https://openalex.org/W2050006154","https://openalex.org/W2060516726","https://openalex.org/W2060815318","https://openalex.org/W2061809273","https://openalex.org/W2075182631","https://openalex.org/W2076299731","https://openalex.org/W2077879229","https://openalex.org/W2082950241","https://openalex.org/W2083932054","https://openalex.org/W2087383805","https://openalex.org/W2099724779","https://openalex.org/W2100627415","https://openalex.org/W2101087886","https://openalex.org/W2107005506","https://openalex.org/W2115516470","https://openalex.org/W2117511045","https://openalex.org/W2120609672","https://openalex.org/W2122904379","https://openalex.org/W2124714582","https://openalex.org/W2125160887","https://openalex.org/W2125680435","https://openalex.org/W2126637410","https://openalex.org/W2127504781","https://openalex.org/W2131347449","https://openalex.org/W2132288458","https://openalex.org/W2133431243","https://openalex.org/W2147818576","https://openalex.org/W2150650678","https://openalex.org/W2151598682","https://openalex.org/W2157726400","https://openalex.org/W2157870551","https://openalex.org/W2159335058","https://openalex.org/W2162234949","https://openalex.org/W2162340487","https://openalex.org/W2165488387","https://openalex.org/W2169749764","https://openalex.org/W2169823808","https://openalex.org/W2169918010","https://openalex.org/W2170981556","https://openalex.org/W2314420468","https://openalex.org/W2786027321","https://openalex.org/W2966207845","https://openalex.org/W3122465213","https://openalex.org/W4231244517","https://openalex.org/W4235637596"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2999103397","https://openalex.org/W2370831213","https://openalex.org/W4315704968","https://openalex.org/W4285478380","https://openalex.org/W2359053655","https://openalex.org/W2100255360","https://openalex.org/W2387777532"],"abstract_inverted_index":{"Centuries":[0],"of":[1,10,27,53,63,99,140,144,151],"biological":[2,92,106],"knowledge":[3],"are":[4],"contained":[5],"in":[6,90,134,147,166],"the":[7,30,47,54,61,91,96,100,163],"massive":[8],"body":[9],"scientific":[11],"literature,":[12],"written":[13],"for":[14,19,82,88,105,137],"human-readability":[15],"but":[16,49,84,116],"too":[17],"big":[18],"any":[20],"one":[21],"person":[22],"to":[23,37,71,95,171],"consume.":[24],"Large-scale":[25],"mining":[26],"information":[28,73,107,154,168],"from":[29,74,155],"literature":[31],"is":[32,36],"necessary":[33],"if":[34],"biology":[35],"transform":[38],"into":[39],"a":[40],"data-driven":[41],"science.":[42,174],"A":[43],"computer":[44],"can":[45],"handle":[46],"volume":[48],"cannot":[50],"make":[51],"sense":[52],"language.":[55,101],"This":[56,158],"paper":[57],"reviews":[58],"and":[59,68,113,123,128,149],"discusses":[60],"use":[62],"natural":[64],"language":[65],"processing":[66],"(NLP)":[67],"machine-learning":[69],"algorithms":[70,78,136],"extract":[72],"systematic":[75],"literature.":[76],"NLP":[77],"have":[79,118],"been":[80,119,132],"used":[81],"decades,":[83],"require":[85,126],"special":[86,97],"development":[87],"application":[89],"realm":[93],"due":[94],"nature":[98],"Many":[102],"tools":[103,170],"exist":[104],"extraction":[108,150,169],"(cellular":[109],"processes,":[110],"taxonomic":[111,141,145,156],"names,":[112],"morphological":[114,152],"characters),":[115],"none":[117],"applied":[120],"life":[121],"wide":[122],"most":[124],"still":[125],"testing":[127],"development.":[129],"Progress":[130],"has":[131],"made":[133],"developing":[135],"automated":[138],"annotation":[139],"text,":[142,148],"identification":[143],"names":[146],"character":[153],"descriptions.":[157],"manuscript":[159],"will":[160],"briefly":[161],"discuss":[162],"key":[164],"steps":[165],"applying":[167],"enhance":[172],"biodiversity":[173]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-22T06:23:43.705686","created_date":"2025-10-10T00:00:00"}