{"id":"https://openalex.org/W2395957288","doi":"https://doi.org/10.3217/jucs-018-05-0623","title":"Improving the Extraction of Text in PDFs by Simulating the Human Reading Order","display_name":"Improving the Extraction of Text in PDFs by Simulating the Human Reading Order","publication_year":2020,"publication_date":"2020-04-07","ids":{"openalex":"https://openalex.org/W2395957288","doi":"https://doi.org/10.3217/jucs-018-05-0623","mag":"2395957288"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.7989","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.7989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jucs.org/jucs_18_5/improving_the_extraction_of/jucs_18_05_0623_0649_hasan.pdf","raw_type":"text"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.3217/jucs-018-05-0623","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051646754","display_name":"Ismael Hasan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ismael Hasan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046723532","display_name":"Javier Parapar","orcid":"https://orcid.org/0000-0002-5997-8252"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Parapar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056469959","display_name":"\u00c1lvaro Barreiro","orcid":"https://orcid.org/0000-0002-6698-2946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u00c1lvaro Barreiro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.996999979019165,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9954000115394592,"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":0.9067789316177368},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6898277997970581},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6449543833732605},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.6066595911979675},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6062765121459961},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5765408277511597},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5100744366645813},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4754776060581207},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4635874927043915},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4306011497974396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40348514914512634},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39742717146873474},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37411361932754517},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1269417107105255}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9067789316177368},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6898277997970581},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6449543833732605},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.6066595911979675},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6062765121459961},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5765408277511597},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5100744366645813},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4754776060581207},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4635874927043915},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4306011497974396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40348514914512634},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39742717146873474},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37411361932754517},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1269417107105255},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.7989","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.7989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jucs.org/jucs_18_5/improving_the_extraction_of/jucs_18_05_0623_0649_hasan.pdf","raw_type":"text"},{"id":"doi:10.3217/jucs-018-05-0623","is_oa":true,"landing_page_url":"https://doi.org/10.3217/jucs-018-05-0623","pdf_url":null,"source":{"id":"https://openalex.org/S4306400660","display_name":"TUGraz OPEN Library (Graz University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4092182","host_organization_name":"Graz University of Technology","host_organization_lineage":["https://openalex.org/I4092182"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"DataPaper"}],"best_oa_location":{"id":"doi:10.3217/jucs-018-05-0623","is_oa":true,"landing_page_url":"https://doi.org/10.3217/jucs-018-05-0623","pdf_url":null,"source":{"id":"https://openalex.org/S4306400660","display_name":"TUGraz OPEN Library (Graz University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4092182","host_organization_name":"Graz University of Technology","host_organization_lineage":["https://openalex.org/I4092182"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"DataPaper"},"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W8079469","https://openalex.org/W1490140361","https://openalex.org/W1769394840","https://openalex.org/W2002393437","https://openalex.org/W2102013417","https://openalex.org/W2105413446","https://openalex.org/W2108959246","https://openalex.org/W2112692009","https://openalex.org/W2129505588","https://openalex.org/W2133115184","https://openalex.org/W2134524813","https://openalex.org/W2135164809","https://openalex.org/W2148528790","https://openalex.org/W2150652226","https://openalex.org/W2155332378","https://openalex.org/W2159767704","https://openalex.org/W2165992492"],"related_works":["https://openalex.org/W2147698110","https://openalex.org/W301308173","https://openalex.org/W3107871225","https://openalex.org/W3123956890","https://openalex.org/W1768944425","https://openalex.org/W3122286688","https://openalex.org/W2100735443","https://openalex.org/W2345306490","https://openalex.org/W2312853652","https://openalex.org/W186995053","https://openalex.org/W1922013683","https://openalex.org/W2065044203","https://openalex.org/W2002393437","https://openalex.org/W3085561018","https://openalex.org/W2387631500","https://openalex.org/W2978154720","https://openalex.org/W2475935882","https://openalex.org/W2767273855","https://openalex.org/W2606303623","https://openalex.org/W3010341014"],"abstract_inverted_index":{"Abstract:":[0],"Text":[1],"preprocessing":[2],"and":[3,10,34,67,126,155,191,199,216],"segmentation":[4],"are":[5,22],"critical":[6],"tasks":[7],"in":[8,25,72,93,147,160,179],"search":[9],"text":[11,90,128,178],"mining":[12],"applications.":[13],"Due":[14],"to":[15,123,151],"the":[16,30,43,54,57,73,81,108,133,136,161,183,210,213],"huge":[17],"amount":[18],"of":[19,29,56,110,132,135,177,202,212],"documents":[20,100],"that":[21,143,181,206],"exclusively":[23],"presented":[24],"PDF":[26,44,62,83,89,137,196],"format,":[27],"most":[28],"Data":[31],"Mining":[32],"(DM)":[33],"Information":[35],"Retrieval":[36],"(IR)":[37],"systems":[38],"must":[39],"extract":[40],"content":[41],"from":[42,60],"files.":[45],"In":[46,117],"some":[47],"occasions":[48],"this":[49,94,106,118],"is":[50,64,107,121,140],"a":[51,61,77,130,144,148,152,172],"difficult":[52],"task:":[53],"result":[55,131],"extraction":[58,91,176,197],"process":[59],"file":[63],"plain":[65],"text,":[66],"it":[68,120,193,207],"should":[69,157],"be":[70,158],"returned":[71],"same":[74],"order":[75],"as":[76,129],"human":[78,184],"would":[79],"read":[80],"original":[82],"file.":[84],"However,":[85],"current":[86],"tools":[87,198,215],"for":[88,175],"fail":[92],"objective":[95],"when":[96],"working":[97],"with":[98,101,114],"complex":[99],"multiple":[102],"columns.":[103],"For":[104],"instance,":[105],"case":[109],"official":[111],"government":[112],"bulletins":[113],"legal":[115,145],"information.":[116],"task,":[119],"mandatory":[122],"get":[124],"correct":[125],"ordered":[127],"application":[134],"extractor.":[138],"It":[139],"very":[141],"usual":[142],"article":[146,154],"document":[149],"refers":[150],"previous":[153],"they":[156],"offered":[159],"right":[162],"sequential":[163],"order.":[164,186],"To":[165],"overcome":[166],"these":[167],"difficulties":[168],"we":[169],"have":[170],"designed":[171],"new":[173],"method":[174,190],"PDFs":[180],"simulates":[182],"reading":[185],"We":[187],"evaluated":[188],"our":[189,203],"compared":[192],"against":[194],"other":[195],"algorithms.":[200,217],"Evaluation":[201],"approach":[204],"shows":[205],"significantly":[208],"outperforms":[209],"results":[211],"existing":[214]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2016-06-24T00:00:00"}