{"id":"https://openalex.org/W2886588919","doi":"https://doi.org/10.4018/jdm.2018040101","title":"Implicit Semantics Based Metadata Extraction and Matching of Scholarly Documents","display_name":"Implicit Semantics Based Metadata Extraction and Matching of Scholarly Documents","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2886588919","doi":"https://doi.org/10.4018/jdm.2018040101","mag":"2886588919"},"language":"en","primary_location":{"id":"doi:10.4018/jdm.2018040101","is_oa":false,"landing_page_url":"https://doi.org/10.4018/jdm.2018040101","pdf_url":null,"source":{"id":"https://openalex.org/S73024538","display_name":"Journal of Database Management","issn_l":"1063-8016","issn":["1063-8016","1533-8010"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Database Management","raw_type":"journal-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/A5036326577","display_name":"Congfeng Jiang","orcid":"https://orcid.org/0000-0003-3592-0328"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congfeng Jiang","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102863611","display_name":"Junming Liu","orcid":"https://orcid.org/0000-0002-9301-0894"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junming Liu","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023208585","display_name":"Dongyang Ou","orcid":"https://orcid.org/0000-0002-9967-9601"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyang Ou","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703531","display_name":"Yumei Wang","orcid":"https://orcid.org/0009-0002-6983-7012"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yumei Wang","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101725542","display_name":"Lifeng Yu","orcid":"https://orcid.org/0000-0002-1805-4790"},"institutions":[{"id":"https://openalex.org/I4210100200","display_name":"China Internet Network Information Center","ror":"https://ror.org/011t9p927","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210100200","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifeng Yu","raw_affiliation_strings":["Hithink RoyalFlush Information Network Co., Ltd., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush Information Network Co., Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I4210100200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9828,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82024592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"29","issue":"2","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9968000054359436,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9968000054359436,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/disk-formatting","display_name":"Disk formatting","score":0.9846662282943726},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8305718302726746},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.771245002746582},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.661818265914917},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.538163423538208},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5043720006942749},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42926114797592163},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3515888750553131},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.295454204082489},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20184963941574097}],"concepts":[{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.9846662282943726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305718302726746},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.771245002746582},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.661818265914917},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.538163423538208},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5043720006942749},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42926114797592163},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3515888750553131},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.295454204082489},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20184963941574097},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4018/jdm.2018040101","is_oa":false,"landing_page_url":"https://doi.org/10.4018/jdm.2018040101","pdf_url":null,"source":{"id":"https://openalex.org/S73024538","display_name":"Journal of Database Management","issn_l":"1063-8016","issn":["1063-8016","1533-8010"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Database Management","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W166924812","https://openalex.org/W791527587","https://openalex.org/W1042149469","https://openalex.org/W1502994231","https://openalex.org/W1550903972","https://openalex.org/W1559499673","https://openalex.org/W1568339100","https://openalex.org/W1603719052","https://openalex.org/W1605010801","https://openalex.org/W1608864735","https://openalex.org/W1987748018","https://openalex.org/W1994874223","https://openalex.org/W1994921100","https://openalex.org/W1995577199","https://openalex.org/W1999595522","https://openalex.org/W2000731427","https://openalex.org/W2005359672","https://openalex.org/W2006404195","https://openalex.org/W2009752265","https://openalex.org/W2020989015","https://openalex.org/W2026961318","https://openalex.org/W2027929866","https://openalex.org/W2029057325","https://openalex.org/W2032861797","https://openalex.org/W2034222664","https://openalex.org/W2042014073","https://openalex.org/W2062644745","https://openalex.org/W2075220845","https://openalex.org/W2091252444","https://openalex.org/W2098564132","https://openalex.org/W2113064181","https://openalex.org/W2129647599","https://openalex.org/W2132083030","https://openalex.org/W2132155482","https://openalex.org/W2139069711","https://openalex.org/W2140339170","https://openalex.org/W2145657314","https://openalex.org/W2168065722","https://openalex.org/W2209407053","https://openalex.org/W2295633004","https://openalex.org/W2301623411","https://openalex.org/W2394521384","https://openalex.org/W2397625158","https://openalex.org/W2438196771","https://openalex.org/W2577020101","https://openalex.org/W4253723135","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2381351160","https://openalex.org/W2361349944","https://openalex.org/W2076264610","https://openalex.org/W2146043838","https://openalex.org/W1556178152","https://openalex.org/W2039476366","https://openalex.org/W2380389143","https://openalex.org/W1757689222","https://openalex.org/W1846541313","https://openalex.org/W3214915308"],"abstract_inverted_index":{"The":[0,18,42,135],"authors":[1,43,79],"propose":[2],"to":[3,38,69,90,113],"use":[4,44,80],"formatting":[5,9,24,46,54,59,95],"templates":[6,55],"and":[7,16,21,31,56,94,126,130,149],"implicit":[8,45],"semantics":[10],"information":[11,25],"for":[12,117],"automatic":[13],"metadata":[14,40,118],"identification":[15],"segmentation.":[17],"pure":[19,92],"texts":[20,93],"their":[22,107,115],"corresponding":[23],"including":[26],"line":[27],"height,":[28],"font":[29,32],"type,":[30],"size,":[33],"are":[34,133,145],"recognized":[35],"in":[36],"parallel":[37],"guide":[39],"identification.":[41],"semantics,":[47],"such":[48],"as":[49,61,63,85],"the":[50,71,78,86,98],"change":[51],"of":[52,97,103,139],"formatting,":[53],"implications,":[57],"explicit":[58],"layouts,":[60],"well":[62],"predefined":[64],"frequently":[65],"occurred":[66],"keywords":[67],"database":[68],"increase":[70],"extraction":[72,137],"accuracy.":[73],"Unlike":[74],"other":[75,127],"OCR-based":[76],"approaches,":[77],"open":[81],"source":[82],"PDFBox":[83,104],"package":[84],"basic":[87],"preprocessing":[88],"tool":[89],"get":[91],"values":[96],"document":[99],"contents.":[100],"On":[101],"top":[102],"they":[105],"built":[106],"own":[108],"pipeline":[109],"program,":[110],"namely,":[111],"PAXAT,":[112],"implement":[114],"approaches":[116],"extraction.":[119],"10177":[120],"papers":[121],"from":[122],"arXiv,":[123],"ACM,":[124],"ACL":[125],"publicly":[128],"accessed":[129],"institution-subscribed":[131],"sources":[132],"tested.":[134],"overall":[136],"accuracy":[138],"title,":[140],"authors,":[141],"affiliations,":[142],"author-affiliation":[143],"matching":[144],"0.9798,":[146],"0.9425,":[147],"0.9298,":[148],"0.9109,":[150],"respectively.":[151]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T06:19:23.411458","created_date":"2025-10-10T00:00:00"}
