{"id":"https://openalex.org/W4238015202","doi":"https://doi.org/10.1109/jcdl.2017.7991564","title":"A Benchmark and Evaluation for Text Extraction from PDF","display_name":"A Benchmark and Evaluation for Text Extraction from PDF","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W4238015202","doi":"https://doi.org/10.1109/jcdl.2017.7991564"},"language":"en","primary_location":{"id":"doi:10.1109/jcdl.2017.7991564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2017.7991564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 ACM/IEEE Joint Conference on Digital Libraries (JCDL)","raw_type":"proceedings-article"},"type":"article","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/A5036444203","display_name":"Hannah Bast","orcid":"https://orcid.org/0000-0003-1213-6776"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hannah Bast","raw_affiliation_strings":["University of Freiburg, Freiburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Freiburg, Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041815504","display_name":"Claudius Korzen","orcid":null},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudius Korzen","raw_affiliation_strings":["University of Freiburg, Freiburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Freiburg, Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036444203"],"corresponding_institution_ids":["https://openalex.org/I161046081"],"apc_list":null,"apc_paid":null,"fwci":3.3185,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.93465277,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9905999898910522,"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":0.9905999898910522,"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/T14330","display_name":"Library Science and Information Systems","score":0.9164000153541565,"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/T11937","display_name":"Research Data Management Practices","score":0.9097999930381775,"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/benchmark","display_name":"Benchmark (surveying)","score":0.9120807647705078},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8526107668876648},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.830021858215332},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6709789037704468},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6590070724487305},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5659611225128174},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5629209280014038},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.47631582617759705},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4421135485172272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3881273567676544},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3760926425457001},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10317867994308472}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.9120807647705078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8526107668876648},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.830021858215332},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6709789037704468},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6590070724487305},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5659611225128174},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5629209280014038},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.47631582617759705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4421135485172272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3881273567676544},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3760926425457001},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10317867994308472},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials 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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcdl.2017.7991564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2017.7991564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 ACM/IEEE Joint Conference on Digital Libraries (JCDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1995111176","https://openalex.org/W1997754546","https://openalex.org/W2002561318","https://openalex.org/W2061598441","https://openalex.org/W2098564132","https://openalex.org/W2166633748","https://openalex.org/W2253675773","https://openalex.org/W2904325185","https://openalex.org/W6648984901","https://openalex.org/W6674887851","https://openalex.org/W6684742833","https://openalex.org/W6691667650","https://openalex.org/W6757015194"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W2378211422","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2130974462"],"abstract_inverted_index":{"Extracting":[0],"the":[1,26,31,36,40,50,68,127,175],"body":[2,53],"text":[3,41,54,145,182],"from":[4,92,107,147,184],"a":[5,21,85,101,116,121,131,186],"PDF":[6,19,96,148,185],"document":[7,51],"is":[8,17,20,58,169],"an":[9,59,137],"important":[10],"but":[11,64,168],"surprisingly":[12],"difficult":[13],"task.":[14],"The":[15],"reason":[16],"that":[18],"layout-based":[22],"format":[23],"which":[24,162],"specifies":[25],"fonts":[27],"and":[28,46,67,95,109,123],"positions":[29],"of":[30,39,61,70,88,103,118,126,130,140],"individual":[32],"characters":[33],"rather":[34],"than":[35],"semantic":[37,128],"units":[38],"(e.g.,":[42,52],"words":[43],"or":[44,55],"paragraphs)":[45],"their":[47,65,71],"role":[48],"in":[49],"caption).":[56],"There":[57],"abundance":[60],"extraction":[62,133,146,183],"tools,":[63,167],"quality":[66],"range":[69],"functionality":[72],"are":[73],"hard":[74],"to":[75,83,153,179],"determine.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"show":[81],"how":[82],"construct":[84,99],"high-quality":[86],"benchmark":[87,102,151],"principally":[89],"arbitrary":[90],"size":[91],"parallel":[93],"TeX":[94],"data.":[97],"We":[98,114,135,156,173],"such":[100],"12,098":[104],"scientific":[105],"articles":[106],"arXiv.org":[108],"make":[110,181],"it":[111],"publicly":[112],"available.":[113],"establish":[115],"set":[117],"criteria":[119],"for":[120,144],"clean":[122],"independent":[124],"assessment":[125],"abilities":[129],"given":[132],"tool.":[134],"provide":[136],"extensive":[138],"evaluation":[139],"14":[141],"state-of-the-art":[142],"tools":[143],"on":[149],"our":[150,154,158],"according":[152],"criteria.":[155],"include":[157],"own":[159],"method,":[160],"Icecite,":[161],"significantly":[163],"outperforms":[164],"all":[165],"other":[166],"still":[170],"not":[171],"perfect.":[172],"outline":[174],"remaining":[176],"steps":[177],"necessary":[178],"finally":[180],"\"solved":[187],"problem\".":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}