{"id":"https://openalex.org/W4323780671","doi":"https://doi.org/10.1007/978-3-031-28032-0_31","title":"A Benchmark of\u00a0PDF Information Extraction Tools Using a\u00a0Multi-task and\u00a0Multi-domain Evaluation Framework for\u00a0Academic Documents","display_name":"A Benchmark of\u00a0PDF Information Extraction Tools Using a\u00a0Multi-task and\u00a0Multi-domain Evaluation Framework for\u00a0Academic Documents","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4323780671","doi":"https://doi.org/10.1007/978-3-031-28032-0_31"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-28032-0_31","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-28032-0_31","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2303.09957","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060549879","display_name":"Norman Meuschke","orcid":"https://orcid.org/0000-0003-4648-8198"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Norman Meuschke","raw_affiliation_strings":["University of G\u00f6ttingen, 37073, G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen, 37073, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036941105","display_name":"Apurva Jagdale","orcid":null},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Apurva Jagdale","raw_affiliation_strings":["University of Passau, 94032, Passau, Germany"],"affiliations":[{"raw_affiliation_string":"University of Passau, 94032, Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041704286","display_name":"Timo Spinde","orcid":"https://orcid.org/0000-0003-3471-4127"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Spinde","raw_affiliation_strings":["University of G\u00f6ttingen, 37073, G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen, 37073, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019466280","display_name":"Jelena Mitrovi\u0107","orcid":"https://orcid.org/0000-0003-3220-8749"},"institutions":[{"id":"https://openalex.org/I2801863878","display_name":"RT-RK Institute for Computer Based Systems (Serbia)","ror":"https://ror.org/02vm8jd66","country_code":"RS","type":"company","lineage":["https://openalex.org/I2801863878"]},{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE","RS"],"is_corresponding":false,"raw_author_name":"Jelena Mitrovi\u0107","raw_affiliation_strings":["The Institute for Artificial Intelligence R &D of Serbia, 21000, Novi Sad, Serbia","University of Passau, 94032, Passau, Germany"],"affiliations":[{"raw_affiliation_string":"The Institute for Artificial Intelligence R &D of Serbia, 21000, Novi Sad, Serbia","institution_ids":["https://openalex.org/I2801863878"]},{"raw_affiliation_string":"University of Passau, 94032, Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"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/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bela Gipp","raw_affiliation_strings":["University of G\u00f6ttingen, 37073, G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen, 37073, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5060549879"],"corresponding_institution_ids":["https://openalex.org/I74656192"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":16.5351,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.99350997,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9980000257492065,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980000257492065,"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":0.9952999949455261,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8349894285202026},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7841142416000366},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7389832139015198},{"id":"https://openalex.org/keywords/header","display_name":"Header","score":0.5846496224403381},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5648557543754578},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5625386238098145},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5433877110481262},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.4898671805858612},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48843589425086975},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4863174855709076},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4218376576900482},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32534700632095337},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2953985929489136},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.155466228723526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349894285202026},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7841142416000366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7389832139015198},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.5846496224403381},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5648557543754578},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5625386238098145},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5433877110481262},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.4898671805858612},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48843589425086975},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4863174855709076},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4218376576900482},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32534700632095337},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2953985929489136},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.155466228723526},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-031-28032-0_31","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-28032-0_31","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2303.09957","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.09957","pdf_url":"https://arxiv.org/pdf/2303.09957","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/132678","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/132678","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"published_version"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2303.09957","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.09957","pdf_url":"https://arxiv.org/pdf/2303.09957","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4323780671.pdf"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W44107710","https://openalex.org/W115105276","https://openalex.org/W791527587","https://openalex.org/W1489253926","https://openalex.org/W1534730506","https://openalex.org/W1559499673","https://openalex.org/W1563075779","https://openalex.org/W1603719052","https://openalex.org/W1995577199","https://openalex.org/W1998839545","https://openalex.org/W2000731427","https://openalex.org/W2009752265","https://openalex.org/W2015814595","https://openalex.org/W2040217811","https://openalex.org/W2079525773","https://openalex.org/W2082470640","https://openalex.org/W2098564132","https://openalex.org/W2104029044","https://openalex.org/W2124303864","https://openalex.org/W2132155482","https://openalex.org/W2147107544","https://openalex.org/W2162630660","https://openalex.org/W2163737492","https://openalex.org/W2172223321","https://openalex.org/W2416987009","https://openalex.org/W2753149099","https://openalex.org/W2765603635","https://openalex.org/W2798010889","https://openalex.org/W2803318469","https://openalex.org/W2806922180","https://openalex.org/W2808479155","https://openalex.org/W2893567907","https://openalex.org/W2912928117","https://openalex.org/W2941922035","https://openalex.org/W2962919508","https://openalex.org/W2964269754","https://openalex.org/W2998138786","https://openalex.org/W3004248957","https://openalex.org/W3009242205","https://openalex.org/W3015453090","https://openalex.org/W3018109885","https://openalex.org/W3023264106","https://openalex.org/W3031676291","https://openalex.org/W3092527850","https://openalex.org/W3113753692","https://openalex.org/W3134359195","https://openalex.org/W3175487048","https://openalex.org/W4238015202","https://openalex.org/W4244512068","https://openalex.org/W4297786773","https://openalex.org/W4398678036","https://openalex.org/W4412258501"],"related_works":["https://openalex.org/W2171597999","https://openalex.org/W2189136227","https://openalex.org/W1866537546","https://openalex.org/W630850086","https://openalex.org/W3200508093","https://openalex.org/W4372053344","https://openalex.org/W3193978431","https://openalex.org/W2379752180","https://openalex.org/W2519240373","https://openalex.org/W2145752793"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2023-03-11T00:00:00"}
