{"id":"https://openalex.org/W2168065722","doi":"https://doi.org/10.1145/2815833.2815834","title":"PDFMEF","display_name":"PDFMEF","publication_year":2015,"publication_date":"2015-09-29","ids":{"openalex":"https://openalex.org/W2168065722","doi":"https://doi.org/10.1145/2815833.2815834","mag":"2168065722"},"language":"en","primary_location":{"id":"doi:10.1145/2815833.2815834","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2815833.2815834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Knowledge Capture","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088286224","display_name":"Jason Killian","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Killian","raw_affiliation_strings":["Computer Science and Engineering, Pennsylvania State University, University Park, PA, 16802 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Pennsylvania State University, University Park, PA, 16802 USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087529969","display_name":"Huaiyu Yang","orcid":"https://orcid.org/0000-0003-2358-1840"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaiyu Yang","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108439761","display_name":"Kyle Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Williams","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112500027","display_name":"Sagnik Ray Choudhury","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sagnik Ray Choudhury","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023506216","display_name":"Suppawong Tuarob","orcid":"https://orcid.org/0000-0002-5201-5699"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suppawong Tuarob","raw_affiliation_strings":["Computer Science and Engineering, Pennsylvania State University, University Park, PA, 16802 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Pennsylvania State University, University Park, PA, 16802 USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089085275","display_name":"Cornelia Caragea","orcid":"https://orcid.org/0000-0002-5664-2163"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cornelia Caragea","raw_affiliation_strings":["Computer Science and Engineering, University of North Texas, Denton, TX, 76203 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of North Texas, Denton, TX, 76203 USA","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA and Computer Science and Engineering, Pennsylvania State University, University Park, PA, 16802 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA and Computer Science and Engineering, Pennsylvania State University, University Park, PA, 16802 USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9927999973297119,"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"}},"topics":[{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9927999973297119,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9909999966621399,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9682000279426575,"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/computer-science","display_name":"Computer science","score":0.8666428327560425},{"id":"https://openalex.org/keywords/header","display_name":"Header","score":0.5937634110450745},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5930606722831726},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5082249641418457},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5076843500137329},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.507609486579895},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.4885185956954956},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.4630430340766907},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.44394177198410034},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4246843457221985},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34538960456848145},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3105279803276062},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.221399188041687},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1119297444820404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8666428327560425},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.5937634110450745},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5930606722831726},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5082249641418457},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5076843500137329},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.507609486579895},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.4885185956954956},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.4630430340766907},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.44394177198410034},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4246843457221985},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34538960456848145},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3105279803276062},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.221399188041687},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1119297444820404},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2815833.2815834","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2815833.2815834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Knowledge Capture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1496737558","https://openalex.org/W1559499673","https://openalex.org/W1568339100","https://openalex.org/W1603719052","https://openalex.org/W1991601938","https://openalex.org/W1991708582","https://openalex.org/W1991869139","https://openalex.org/W2009556891","https://openalex.org/W2020280480","https://openalex.org/W2023704244","https://openalex.org/W2035050715","https://openalex.org/W2042014073","https://openalex.org/W2048135704","https://openalex.org/W2057954853","https://openalex.org/W2090518279","https://openalex.org/W2091344457","https://openalex.org/W2096797897","https://openalex.org/W2098564132","https://openalex.org/W2131257962","https://openalex.org/W2140479099","https://openalex.org/W2295508865","https://openalex.org/W2296157284","https://openalex.org/W2399166302","https://openalex.org/W2577020101","https://openalex.org/W2602331152","https://openalex.org/W2736801446","https://openalex.org/W6893261241"],"related_works":["https://openalex.org/W2171597999","https://openalex.org/W2189136227","https://openalex.org/W1866537546","https://openalex.org/W2016355461","https://openalex.org/W2386938185","https://openalex.org/W1986386500","https://openalex.org/W2068844411","https://openalex.org/W2793744252","https://openalex.org/W2072284316","https://openalex.org/W1516746680"],"abstract_inverted_index":{"We":[0],"introduce":[1],"PDFMEF,":[2],"a":[3,19,70,94,116,134,147,154,193,201],"multi-entity":[4],"knowledge":[5,195],"extraction":[6,24,62,73,88],"framework":[7,20,102],"for":[8,32,43,47,51,55],"scholarly":[9,37,187,203],"documents":[10,188],"in":[11,41,75,113,119,137,185,197],"the":[12,36,72,99,124,138],"PDF":[13,168],"format.":[14],"It":[15,170],"is":[16,78,103,109,129,171,209],"implemented":[17],"with":[18,86,126],"that":[21,123],"encapsulates":[22],"open-source":[23],"tools.":[25],"Currently,":[26],"it":[27,65,142,208],"leverages":[28],"PDFBox":[29],"and":[30,57,60,108,132,177,189],"TET":[31],"full":[33],"text":[34],"extraction,":[35,49,53,59],"document":[38,44],"filter":[39],"described":[40],"[5]":[42],"classification,":[45],"GROBID":[46],"header":[48],"ParsCit":[50],"citation":[52],"PDFFigures":[54],"figure":[56],"table":[58],"algorithm":[61],"[27].":[63],"While":[64],"can":[66,82],"be":[67,106],"run":[68,145],"as":[69],"whole,":[71],"tool":[74],"each":[76],"module":[77],"highly":[79],"customizable.":[80],"Users":[81],"substitute":[83],"default":[84,127],"extractors":[85],"other":[87],"tools":[89],"they":[90],"prefer":[91],"by":[92],"writing":[93],"thin":[95],"wrapper":[96],"to":[97,105,144,165,173,180,190,199],"implement":[98],"abstracts.":[100],"The":[101,150],"designed":[104],"scalable":[107],"capable":[110],"of":[111,157,207],"running":[112,210],"parallel":[114],"using":[115,153],"multi-processing":[117],"technique":[118],"Python.":[120],"Experiments":[121],"indicate":[122],"system":[125],"setups":[128],"CPU":[130],"bounded,":[131],"leaves":[133],"small":[135],"footprint":[136],"memory,":[139],"which":[140],"makes":[141],"best":[143,151],"on":[146,163,211],"multi-core":[148],"machine.":[149],"performance":[152],"dedicated":[155],"server":[156],"16":[158],"cores":[159],"takes":[160],"1.3":[161],"seconds":[162],"average":[164],"process":[166],"one":[167],"document.":[169],"used":[172],"index":[174],"extracted":[175],"information":[176],"help":[178],"users":[179],"quickly":[181],"locate":[182],"relevant":[183],"results":[184],"published":[186],"efficiently":[191],"construct":[192],"large":[194],"base":[196],"order":[198],"build":[200],"semantic":[202],"search":[204,215],"engine.":[205,216],"Part":[206],"CiteSeerX":[212],"digital":[213],"library":[214]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}
