{"id":"https://openalex.org/W3045066314","doi":"https://doi.org/10.1145/3383583.3398590","title":"A Heuristic Baseline Method for Metadata Extraction from Scanned Electronic Theses and Dissertations","display_name":"A Heuristic Baseline Method for Metadata Extraction from Scanned Electronic Theses and Dissertations","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3045066314","doi":"https://doi.org/10.1145/3383583.3398590","mag":"3045066314"},"language":"en","primary_location":{"id":"doi:10.1145/3383583.3398590","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digitalcommons.odu.edu/cgi/viewcontent.cgi?article=1171&context=computerscience_fac_pubs","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072339879","display_name":"Muntabir Hasan Choudhury","orcid":"https://orcid.org/0000-0002-9318-8844"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Muntabir Hasan Choudhury","raw_affiliation_strings":["Old Dominion University, Norfolk, VA, USA"],"affiliations":[{"raw_affiliation_string":"Old Dominion University, Norfolk, VA, USA","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Old Dominion University, Norfolk, VA, USA"],"affiliations":[{"raw_affiliation_string":"Old Dominion University, Norfolk, VA, USA","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062743697","display_name":"William A. Ingram","orcid":"https://orcid.org/0000-0002-8307-8844"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William A. Ingram","raw_affiliation_strings":["Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049148461","display_name":"Edward A. Fox","orcid":"https://orcid.org/0000-0003-1447-6870"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward A. Fox","raw_affiliation_strings":["Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072339879"],"corresponding_institution_ids":["https://openalex.org/I81365321"],"apc_list":null,"apc_paid":null,"fwci":2.2882,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.92516037,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"515","last_page":"516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9916999936103821,"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/T11937","display_name":"Research Data Management Practices","score":0.9898999929428101,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.9548537731170654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7396411895751953},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6889903545379639},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6604147553443909},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6482941508293152},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.5261801481246948},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.49520817399024963},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.45002371072769165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2675591707229614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09265574812889099}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9548537731170654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7396411895751953},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6889903545379639},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6604147553443909},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6482941508293152},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5261801481246948},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49520817399024963},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.45002371072769165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2675591707229614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09265574812889099},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3383583.3398590","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:digitalcommons.odu.edu:computerscience_fac_pubs-1171","is_oa":true,"landing_page_url":"https://digitalcommons.odu.edu/computerscience_fac_pubs/169","pdf_url":"https://digitalcommons.odu.edu/cgi/viewcontent.cgi?article=1171&context=computerscience_fac_pubs","source":{"id":"https://openalex.org/S4377196314","display_name":"ODU Digital Commons (Old Dominion University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I81365321","host_organization_name":"Old Dominion University","host_organization_lineage":["https://openalex.org/I81365321"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Faculty Publications","raw_type":"conference"}],"best_oa_location":{"id":"pmh:oai:digitalcommons.odu.edu:computerscience_fac_pubs-1171","is_oa":true,"landing_page_url":"https://digitalcommons.odu.edu/computerscience_fac_pubs/169","pdf_url":"https://digitalcommons.odu.edu/cgi/viewcontent.cgi?article=1171&context=computerscience_fac_pubs","source":{"id":"https://openalex.org/S4377196314","display_name":"ODU Digital Commons (Old Dominion University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I81365321","host_organization_name":"Old Dominion University","host_organization_lineage":["https://openalex.org/I81365321"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Faculty Publications","raw_type":"conference"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1471725967","display_name":null,"funder_award_id":"LG-37-19-0078-19","funder_id":"https://openalex.org/F4320306122","funder_display_name":"Institute of Museum and Library Services"}],"funders":[{"id":"https://openalex.org/F4320306122","display_name":"Institute of Museum and Library Services","ror":"https://ror.org/030prv062"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3045066314.pdf","grobid_xml":"https://content.openalex.org/works/W3045066314.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1603719052","https://openalex.org/W2098564132","https://openalex.org/W2286291649","https://openalex.org/W2962905462","https://openalex.org/W4253723135"],"related_works":["https://openalex.org/W2153783156","https://openalex.org/W2185857879","https://openalex.org/W2173249046","https://openalex.org/W2910421009","https://openalex.org/W1967754619","https://openalex.org/W2099528054","https://openalex.org/W2108481583","https://openalex.org/W3166717111","https://openalex.org/W1556418350","https://openalex.org/W2360874655"],"abstract_inverted_index":{"Extracting":[0],"metadata":[1,50,92,115,165],"from":[2,51,166],"scholarly":[3,22],"papers":[4,23],"is":[5,86,105,158],"an":[6,128],"important":[7],"text":[8,69,140],"mining":[9],"problem.":[10],"Widely":[11],"used":[12],"open-source":[13],"tools":[14],"such":[15,30],"as":[16,31],"GROBID":[17],"are":[18],"designed":[19,80],"for":[20,27,83,90,148],"born-digital":[21],"but":[24],"often":[25],"fail":[26],"scanned":[28,56,63],"documents,":[29],"Electronic":[32],"Theses":[33],"and":[34,67,101,121],"Dissertations":[35],"(ETDs).":[36],"Here":[37],"we":[38],"present":[39],"a":[40,45,76,108,145],"preliminary":[41],"baseline":[42,147],"work":[43,161],"with":[44,61],"heuristic":[46,125],"model":[47],"to":[48,132,163],"extract":[49,164],"the":[52,118,135,138,159],"cover":[53],"pages":[54,64],"of":[55,78,113,130,137],"ETDs.":[57,168],"The":[58,103],"process":[59],"started":[60],"converting":[62],"into":[65],"images":[66],"then":[68],"files":[70],"by":[71,117],"applying":[72],"OCR":[73],"tools.":[74],"Then":[75],"series":[77],"carefully":[79],"regular":[81],"expressions":[82],"each":[84],"field":[85],"applied,":[87],"capturing":[88],"patterns":[89],"seven":[91],"fields:":[93],"titles,":[94],"authors,":[95],"years,":[96],"degrees,":[97],"academic":[98],"programs,":[99],"institutions,":[100],"advisors.":[102],"method":[104,126,143],"evaluated":[106],"on":[107,134],"ground":[109],"truth":[110],"dataset":[111],"comprised":[112],"rectified":[114],"provided":[116],"Virginia":[119],"Tech":[120],"MIT":[122],"libraries.":[123],"Our":[124,142],"achieves":[127],"accuracy":[129],"up":[131],"97%":[133],"fields":[136],"ETD":[139],"files.":[141],"poses":[144],"strong":[146],"machine":[149],"learning":[150],"based":[151],"methods.":[152],"To":[153],"our":[154],"best":[155],"knowledge,":[156],"this":[157],"first":[160],"attempting":[162],"non-born-digital":[167]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}