{"id":"https://openalex.org/W3137033356","doi":"https://doi.org/10.1109/bigdata50022.2020.9377737","title":"General Self-aware Information Extraction from Labels of Biological Collections","display_name":"General Self-aware Information Extraction from Labels of Biological Collections","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3137033356","doi":"https://doi.org/10.1109/bigdata50022.2020.9377737","mag":"3137033356"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027673766","display_name":"Icaro Alzuru","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Icaro Alzuru","raw_affiliation_strings":["ACIS Laboratory, University of Florida, Gainesville, USA"],"affiliations":[{"raw_affiliation_string":"ACIS Laboratory, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003262238","display_name":"Andr\u00e9a Matsunaga","orcid":"https://orcid.org/0000-0001-9036-5895"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Matsunaga","raw_affiliation_strings":["ACIS Laboratory, University of Florida, Gainesville, USA"],"affiliations":[{"raw_affiliation_string":"ACIS Laboratory, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086302230","display_name":"Maur\u00edcio Tsugawa","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mauricio Tsugawa","raw_affiliation_strings":["ACIS Laboratory, University of Florida, Gainesville, USA"],"affiliations":[{"raw_affiliation_string":"ACIS Laboratory, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003181544","display_name":"J.A.B. Fortes","orcid":"https://orcid.org/0000-0001-8870-5205"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose A.B. Fortes","raw_affiliation_strings":["ACIS Laboratory, University of Florida, Gainesville, USA"],"affiliations":[{"raw_affiliation_string":"ACIS Laboratory, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027673766"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.13985208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3035","last_page":"3044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9973000288009644,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9973000288009644,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9965000152587891,"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/T10895","display_name":"Species Distribution and Climate Change","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental 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":0.821101188659668},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.7306152582168579},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6876974105834961},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5917707085609436},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5508168935775757},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5220898985862732},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5104931592941284},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.49078473448753357},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.48443105816841125},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4621959328651428},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44963711500167847},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.44785693287849426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4047431945800781},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32739126682281494},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.29233622550964355},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.19807583093643188},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1465592086315155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821101188659668},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7306152582168579},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6876974105834961},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5917707085609436},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5508168935775757},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5220898985862732},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5104931592941284},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.49078473448753357},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.48443105816841125},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4621959328651428},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44963711500167847},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.44785693287849426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4047431945800781},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32739126682281494},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.29233622550964355},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.19807583093643188},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1465592086315155},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1498266716","https://openalex.org/W1521125545","https://openalex.org/W1987248861","https://openalex.org/W2018518088","https://openalex.org/W2046055655","https://openalex.org/W2107556918","https://openalex.org/W2113053869","https://openalex.org/W2171313960","https://openalex.org/W2179652410","https://openalex.org/W2239231358","https://openalex.org/W2327209116","https://openalex.org/W2768488789","https://openalex.org/W2769563307","https://openalex.org/W2794248503","https://openalex.org/W2901476362","https://openalex.org/W2963530158","https://openalex.org/W3008048863","https://openalex.org/W3011970228","https://openalex.org/W6631217535"],"related_works":["https://openalex.org/W2334378031","https://openalex.org/W2916255597","https://openalex.org/W2999302224","https://openalex.org/W3091569222","https://openalex.org/W4241018868","https://openalex.org/W1495833002","https://openalex.org/W2075635421","https://openalex.org/W2964631078","https://openalex.org/W3160627956","https://openalex.org/W3006227201"],"abstract_inverted_index":{"The":[0,26,93,160,181,215],"information":[1],"stored":[2],"in":[3,43,187],"biological":[4],"collections":[5],"can":[6,116],"help":[7],"us":[8],"model":[9,104,184],"biodiversity,":[10],"develop":[11],"new":[12],"medicines,":[13],"control":[14],"agricultural":[15],"pests,":[16],"and":[17,151,205],"understand":[18],"or":[19,57],"avoid":[20],"epidemics,":[21],"among":[22],"many":[23],"other":[24,149],"benefits.":[25],"digitization":[27],"of":[28,34,71,90,108,135,144,148,167,175,190,194,200,203,211,217],"this":[29,79],"information,":[30],"including":[31],"the":[32,35,41,87,106,109,113,120,125,156,165,173,188,208],"transcription":[33,166],"Darwin":[36],"Core":[37],"(DC)":[38],"terms":[39,169],"from":[40,55,59,119,142,155],"text":[42,115],"photographs,":[44],"is":[45],"currently":[46],"performed":[47],"through":[48],"human-oriented":[49],"processes":[50],"that":[51],"rely":[52],"on":[53,213],"input":[54],"experts":[56],"consensus":[58],"crowdsourced":[60,96],"work.":[61],"Previous":[62],"studies":[63],"utilized":[64],"heuristics,":[65],"only":[66],"applicable":[67],"to":[68,98,207],"a":[69,83,101,131,178,191,198],"couple":[70],"DC":[72,91,110,168],"terms,":[73,196],"for":[74,86,105],"their":[75],"semi-automated":[76],"extraction.":[77],"In":[78],"paper,":[80],"we":[81],"propose":[82],"human-in-the-loop":[84,162],"workflow":[85,94],"general":[88],"extraction":[89,107,174,189],"terms.":[92,111],"utilizes":[95],"data":[97,152,210],"iteratively":[99],"train":[100],"named-entity":[102,182],"recognition":[103,123,183],"Because":[112],"source":[114],"contain":[117],"errors":[118],"optical":[121],"character":[122],"process,":[124],"extracted":[126,154],"values":[127,176],"are":[128,140],"validated":[129],"by":[130,170,223],"confidence":[132],"estimation":[133],"structure":[134],"frequency":[136],"lists.":[137],"These":[138],"lists":[139],"created":[141],"millions":[143],"previously":[145],"digitized":[146],"records,":[147],"collections,":[150],"already":[153],"collection":[157],"being":[158],"processed.":[159],"proposed":[161],"approach":[163],"accelerates":[164],"partially":[171],"automating":[172],"with":[177],"near-human":[179],"quality.":[180],"was":[185,221],"tested":[186],"heterogeneous":[192],"group":[193],"10":[195],"obtaining":[197],"recall":[199],"0.859,":[201],"precision":[202],"0.931,":[204],"similarity":[206],"ground-truth":[209],"0.941,":[212],"average.":[214],"number":[216],"required":[218],"crowdsourcing":[219],"sessions":[220],"reduced":[222],"84%.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}