{"id":"https://openalex.org/W2098564132","doi":"https://doi.org/10.1145/2467696.2467753","title":"Evaluation of header metadata extraction approaches and tools for scientific PDF documents","display_name":"Evaluation of header metadata extraction approaches and tools for scientific PDF documents","publication_year":2013,"publication_date":"2013-07-22","ids":{"openalex":"https://openalex.org/W2098564132","doi":"https://doi.org/10.1145/2467696.2467753","mag":"2098564132"},"language":"en","primary_location":{"id":"doi:10.1145/2467696.2467753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2467696.2467753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://nbn-resolving.de/urn:nbn:de:bsz:352-0-285622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062269057","display_name":"Mario Lipinski","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mario Lipinski","raw_affiliation_strings":["UC Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032316523","display_name":"Kevin Yao","orcid":"https://orcid.org/0000-0001-6369-655X"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Yao","raw_affiliation_strings":["UC Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013617539","display_name":"Corinna Breitinger","orcid":"https://orcid.org/0000-0001-6586-0392"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Corinna Breitinger","raw_affiliation_strings":["UC Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081348430","display_name":"Joeran Beel","orcid":"https://orcid.org/0000-0002-4537-5573"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joeran Beel","raw_affiliation_strings":["UC Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058837356","display_name":"B\u00e9la Gipp","orcid":"https://orcid.org/0000-0001-6522-3019"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bela Gipp","raw_affiliation_strings":["UC Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.5592,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.98923101,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"385","last_page":"386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9907000064849854,"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"}},"topics":[{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9907000064849854,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9889000058174133,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9225999712944031,"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/metadata","display_name":"Metadata","score":0.9409642219543457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8208479881286621},{"id":"https://openalex.org/keywords/header","display_name":"Header","score":0.6958822011947632},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.6266147494316101},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.6131336092948914},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.5984058976173401},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.548143744468689},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5327544212341309},{"id":"https://openalex.org/keywords/meta-data-services","display_name":"Meta Data Services","score":0.5058541297912598},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4767338037490845},{"id":"https://openalex.org/keywords/metadata-management","display_name":"Metadata management","score":0.47592929005622864},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46766769886016846},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.4308326542377472},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.41956204175949097},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.361667662858963},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09212970733642578}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9409642219543457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8208479881286621},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.6958822011947632},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.6266147494316101},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.6131336092948914},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.5984058976173401},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.548143744468689},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5327544212341309},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.5058541297912598},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4767338037490845},{"id":"https://openalex.org/C2779489174","wikidata":"https://www.wikidata.org/wiki/Q6822246","display_name":"Metadata management","level":3,"score":0.47592929005622864},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46766769886016846},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.4308326542377472},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.41956204175949097},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.361667662858963},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09212970733642578},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/2467696.2467753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2467696.2467753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.734.7848","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.734.7848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://docear.org/papers/Evaluation_of_Header_Metadata_Extraction_Approaches_and_Tools_for_Scientific_PDF_Documents.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.820.7748","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.820.7748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://kops.uni-konstanz.de/bitstream/handle/123456789/30950/Lipinski_0-285622.pdf%3Bjsessionid%3DDA80B5896C55134802E26AD58A7EBA0E?sequence%3D1","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.821.1421","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.821.1421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://gipp.com/wp-content/papercite-data/pdf/lipinski13.pdf","raw_type":"text"},{"id":"pmh:oai:kops.uni-konstanz.de:123456789/30950","is_oa":true,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bsz:352-0-285622","pdf_url":null,"source":{"id":"https://openalex.org/S4377196311","display_name":"KOPS (University of Konstanz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189712700","host_organization_name":"University of Konstanz","host_organization_lineage":["https://openalex.org/I189712700"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/106798","is_oa":false,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/106798","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"no"}],"best_oa_location":{"id":"pmh:oai:kops.uni-konstanz.de:123456789/30950","is_oa":true,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bsz:352-0-285622","pdf_url":null,"source":{"id":"https://openalex.org/S4377196311","display_name":"KOPS (University of Konstanz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189712700","host_organization_name":"University of Konstanz","host_organization_lineage":["https://openalex.org/I189712700"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1605010801","https://openalex.org/W2005359672","https://openalex.org/W2082470640","https://openalex.org/W2090977244","https://openalex.org/W2151220468","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3084772717","https://openalex.org/W2907247951","https://openalex.org/W2374379029","https://openalex.org/W2380261968","https://openalex.org/W2376038160","https://openalex.org/W3199469221","https://openalex.org/W1512114296","https://openalex.org/W2018424284","https://openalex.org/W2389784781","https://openalex.org/W2537325806"],"abstract_inverted_index":{"This":[0,29],"paper":[1],"evaluates":[2],"the":[3,8,24,40,55,71,76,94],"performance":[4],"of":[5,10,26,59],"tools":[6,61],"for":[7,22,35],"extraction":[9,17,46],"metadata":[11,16,45,95],"from":[12,70],"scientific":[13],"articles.":[14],"Accurate":[15],"is":[18,32],"an":[19],"important":[20],"task":[21],"automating":[23],"management":[25],"digital":[27],"libraries.":[28],"comparative":[30],"study":[31],"a":[33],"guide":[34],"developers":[36],"looking":[37],"to":[38,97],"integrate":[39],"most":[41],"suitable":[42],"and":[43,57,86],"effective":[44],"tool":[47],"into":[48],"their":[49],"software.":[50],"We":[51],"shed":[52],"light":[53],"on":[54,93],"strengths":[56],"weaknesses":[58],"seven":[60],"in":[62],"common":[63],"use.":[64],"In":[65],"our":[66],"evaluation":[67],"using":[68],"papers":[69],"arXiv":[72],"collection,":[73],"GROBID":[74],"delivered":[75,89],"best":[77],"results,":[78],"followed":[79],"by":[80],"Mendeley":[81],"Desktop.":[82],"SciPlore":[83],"Xtract,":[84],"PDFMeat,":[85],"SVMHeaderParse":[87],"also":[88],"good":[90],"results":[91],"depending":[92],"type":[96],"be":[98],"extracted.":[99]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":5}],"updated_date":"2026-06-14T07:44:22.658603","created_date":"2025-10-10T00:00:00"}
