{"id":"https://openalex.org/W4313291246","doi":"https://doi.org/10.1109/access.2022.3233228","title":"Annotated Open Corpus Construction and BERT-Based Approach for Automatic Metadata Extraction From Korean Academic Papers","display_name":"Annotated Open Corpus Construction and BERT-Based Approach for Automatic Metadata Extraction From Korean Academic Papers","publication_year":2022,"publication_date":"2022-12-29","ids":{"openalex":"https://openalex.org/W4313291246","doi":"https://doi.org/10.1109/access.2022.3233228"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3233228","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3233228","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10003205.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10003205.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042948850","display_name":"Hyesoo Kong","orcid":"https://orcid.org/0000-0002-3742-7433"},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyesoo Kong","raw_affiliation_strings":["Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-3742-7433","affiliations":[{"raw_affiliation_string":"Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100536917","display_name":"Hwa-Mook Yoon","orcid":null},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwamook Yoon","raw_affiliation_strings":["Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073681256","display_name":"Jae-Wook Seol","orcid":null},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewook Seol","raw_affiliation_strings":["Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041026063","display_name":"Mi-Hwan Hyun","orcid":null},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mihwan Hyun","raw_affiliation_strings":["Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009196523","display_name":"Hyejin Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyejin Lee","raw_affiliation_strings":["Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046389164","display_name":"Soonyoung Kim","orcid":"https://orcid.org/0000-0002-7499-383X"},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soonyoung Kim","raw_affiliation_strings":["Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101524567","display_name":"Wonjun Choi","orcid":"https://orcid.org/0000-0002-9711-0091"},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonjun Choi","raw_affiliation_strings":["Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-9711-0091","affiliations":[{"raw_affiliation_string":"Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I878022262"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I878022262"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2624,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62697666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"11","issue":null,"first_page":"825","last_page":"838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9884999990463257,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9884999990463257,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9879999756813049,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9749000072479248,"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/metadata","display_name":"Metadata","score":0.864766001701355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8169357180595398},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5767873525619507},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.438988596200943},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4303331971168518},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.42966189980506897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3931244909763336}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.864766001701355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169357180595398},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5767873525619507},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.438988596200943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4303331971168518},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.42966189980506897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3931244909763336},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3233228","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3233228","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10003205.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:859f68b7f15c45ff830a8a75b6c301db","is_oa":true,"landing_page_url":"https://doaj.org/article/859f68b7f15c45ff830a8a75b6c301db","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 825-838 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3233228","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3233228","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10003205.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G140130440","display_name":null,"funder_award_id":"K-22-L01-C01-S01","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G5879898452","display_name":null,"funder_award_id":"K-22-L01-C01-S01","funder_id":"https://openalex.org/F4320322105","funder_display_name":"Korea Institute of Science and Technology Information"}],"funders":[{"id":"https://openalex.org/F4320322091","display_name":"Korea Institute of Science and Technology","ror":"https://ror.org/05kzfa883"},{"id":"https://openalex.org/F4320322105","display_name":"Korea Institute of Science and Technology Information","ror":"https://ror.org/01k4yrm29"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313291246.pdf","grobid_xml":"https://content.openalex.org/works/W4313291246.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W791527587","https://openalex.org/W1603719052","https://openalex.org/W1647671624","https://openalex.org/W1762166282","https://openalex.org/W1940872118","https://openalex.org/W1981791873","https://openalex.org/W2000731427","https://openalex.org/W2015814595","https://openalex.org/W2053154970","https://openalex.org/W2080928448","https://openalex.org/W2107068745","https://openalex.org/W2124303864","https://openalex.org/W2145657314","https://openalex.org/W2158755884","https://openalex.org/W2164777277","https://openalex.org/W2206373005","https://openalex.org/W2525778437","https://openalex.org/W2626407095","https://openalex.org/W2781934638","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2918555272","https://openalex.org/W2937573492","https://openalex.org/W2939507640","https://openalex.org/W2963469006","https://openalex.org/W2970771982","https://openalex.org/W2991170427","https://openalex.org/W3102927624","https://openalex.org/W3213294137","https://openalex.org/W4225358744","https://openalex.org/W4239510810","https://openalex.org/W4253723135","https://openalex.org/W4285222470","https://openalex.org/W6636915900","https://openalex.org/W6640362995","https://openalex.org/W6682082992","https://openalex.org/W6727690538","https://openalex.org/W6755207826","https://openalex.org/W6761748628"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248"],"abstract_inverted_index":{"With":[0],"the":[1,8,41,54,95,123,153,163,171,177,188,207,227],"accelerating":[2],"development":[3],"of":[4,57,62,66,125,162,170,211,234],"science":[5,23,50],"and":[6,24,45,51,64,114,150,157,165,186,214,221],"technology,":[7],"academic":[9,59,112,247],"papers":[10,20,79,107,248],"being":[11,82],"published":[12],"in":[13,22,49,99,241,249],"various":[14,250],"fields":[15,26],"are":[16,27,68],"increasing":[17],"rapidly.":[18],"Academic":[19],"specially":[21],"technology":[25],"a":[28,159],"crucial":[29],"media":[30],"for":[31,121,128,152],"researchers":[32],"who":[33],"develop":[34],"new":[35,201],"technologies":[36],"by":[37],"identifying":[38],"knowledge":[39],"regarding":[40],"latest":[42],"technological":[43],"trends":[44],"conduct":[46],"derivative":[47],"studies":[48],"technology.":[52],"Therefore,":[53],"continual":[55],"collection":[56],"extensive":[58],"papers,":[60,213],"structuring":[61],"metadata,":[63],"construction":[65],"databases":[67],"significant":[69],"tasks.":[70],"However,":[71],"research":[72],"on":[73],"automatic":[74,126,242],"metadata":[75,130,208,243],"extraction":[76,127,209,244],"from":[77,104,132,245],"Korean":[78,89,111,212,246],"is":[80,138],"not":[81],"actively":[83],"conducted":[84],"currently":[85],"owing":[86],"to":[87,102,109,194],"insufficient":[88],"training":[90,122,202],"data.":[91,167],"We":[92],"automatically":[93,154],"constructed":[94,155],"largest":[96],"labeled":[97,116,136],"corpus":[98,117,137],"South":[100],"Korea":[101],"date":[103],"315,320":[105],"PDF":[106,133],"belonging":[108],"503":[110],"journals":[113],"this":[115],"can":[118,205],"be":[119],"used":[120],"models":[124],"12":[129],"types":[131],"papers.":[134],"This":[135],"available":[139],"at":[140],"<uri":[141],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[142],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://doi.org/10.23057/48</uri>":[143],".":[144],"Moreover,":[145],"we":[146,184,199,218],"developed":[147,219],"inspection":[148,161],"process":[149],"guidelines":[151],"data":[156,173],"performed":[158],"full":[160],"validation":[164],"testing":[166],"The":[168,224],"reliability":[169],"inspected":[172],"was":[174],"verified":[175],"through":[176,215],"inter-annotator":[178],"agreement":[179],"measurement.":[180],"Using":[181],"our":[182],"corpus,":[183],"trained":[185],"evaluated":[187],"BERT":[189],"based":[190],"transfer":[191],"learning":[192],"model":[193],"verify":[195],"its":[196],"reliability.":[197],"Furthermore,":[198],"proposed":[200],"methods":[203],"that":[204],"improve":[206],"performance":[210,229,240],"these":[216],"methods,":[217],"KorSciBERT-ME-J":[220,225],"KorSciBERT-ME-J+C":[222],"models.":[223],"showed":[226],"highest":[228],"with":[230],"an":[231],"F1":[232],"score":[233],"99.36%,":[235],"as":[236,238],"well":[237],"robust":[239],"formats.":[251]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}