{"id":"https://openalex.org/W2166633748","doi":"https://doi.org/10.1186/1751-0473-7-7","title":"Layout-aware text extraction from full-text PDF of scientific articles","display_name":"Layout-aware text extraction from full-text PDF of scientific articles","publication_year":2012,"publication_date":"2012-05-28","ids":{"openalex":"https://openalex.org/W2166633748","doi":"https://doi.org/10.1186/1751-0473-7-7","mag":"2166633748","pmid":"https://pubmed.ncbi.nlm.nih.gov/22640904"},"language":"en","primary_location":{"id":"doi:10.1186/1751-0473-7-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1751-0473-7-7","pdf_url":"https://scfbm.biomedcentral.com/track/pdf/10.1186/1751-0473-7-7","source":{"id":"https://openalex.org/S45786803","display_name":"Source Code for Biology and Medicine","issn_l":"1751-0473","issn":["1751-0473"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Source Code for Biology and Medicine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://scfbm.biomedcentral.com/track/pdf/10.1186/1751-0473-7-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112629679","display_name":"C. R. Ramakrishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cartic Ramakrishnan","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA, 90292-6695, USA. cartic@isi.edu","Information Sciences Institute, University of Southern California, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA, 90292-6695, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA, 90292-6695, USA. cartic@isi.edu","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA, 90292-6695, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042684601","display_name":"Abhishek Patnia","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210164117","display_name":"Walker (United States)","ror":"https://ror.org/05hgh7849","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164117"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Patnia","raw_affiliation_strings":["Computer Science Department, University of Southern California, 941 Bloom Walker, Los Angeles, CA, 90089-0781, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Southern California, 941 Bloom Walker, Los Angeles, CA, 90089-0781, USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210164117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060225743","display_name":"Eduard Hovy","orcid":"https://orcid.org/0000-0002-3270-7903"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eduard Hovy","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA, 90292-6695, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA, 90292-6695, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087346345","display_name":"Gully Burns","orcid":"https://orcid.org/0000-0003-1493-865X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gully APC Burns","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA, 90292-6695, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA, 90292-6695, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112629679"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":{"value":2040,"currency":"USD","value_usd":2040},"apc_paid":{"value":2040,"currency":"USD","value_usd":2040},"fwci":8.2976,"has_fulltext":true,"cited_by_count":130,"citation_normalized_percentile":{"value":0.97372468,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"7","issue":"1","first_page":"7","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.29899999499320984,"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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.29899999499320984,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.2775999903678894,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.16840000450611115,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8477143049240112},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6925429105758667},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5692746639251709},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.4755396842956543},{"id":"https://openalex.org/keywords/text-graph","display_name":"Text graph","score":0.44537028670310974},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4389193058013916},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3935111165046692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3345608115196228},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.19238683581352234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8477143049240112},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6925429105758667},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5692746639251709},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.4755396842956543},{"id":"https://openalex.org/C66945725","wikidata":"https://www.wikidata.org/wiki/Q18388823","display_name":"Text graph","level":3,"score":0.44537028670310974},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4389193058013916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3935111165046692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3345608115196228},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.19238683581352234},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/1751-0473-7-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1751-0473-7-7","pdf_url":"https://scfbm.biomedcentral.com/track/pdf/10.1186/1751-0473-7-7","source":{"id":"https://openalex.org/S45786803","display_name":"Source Code for Biology and Medicine","issn_l":"1751-0473","issn":["1751-0473"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Source Code for Biology and Medicine","raw_type":"journal-article"},{"id":"pmid:22640904","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22640904","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Source code for biology and medicine","raw_type":null},{"id":"pmh:oai:doaj.org/article:02abe9002d8345419466c56d946a6c6b","is_oa":false,"landing_page_url":"https://doaj.org/article/02abe9002d8345419466c56d946a6c6b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Source Code for Biology and Medicine, Vol 7, Iss 1, p 7 (2012)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:3441580","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3441580","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Source Code Biol Med","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1751-0473-7-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1751-0473-7-7","pdf_url":"https://scfbm.biomedcentral.com/track/pdf/10.1186/1751-0473-7-7","source":{"id":"https://openalex.org/S45786803","display_name":"Source Code for Biology and Medicine","issn_l":"1751-0473","issn":["1751-0473"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Source Code for Biology and Medicine","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G182816247","display_name":null,"funder_award_id":"R01 GM083871","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G2032847650","display_name":null,"funder_award_id":"U24 RR025736-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3651620967","display_name":null,"funder_award_id":"U24 RR025736","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4098347278","display_name":null,"funder_award_id":"U24 GM104203","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G5779719627","display_name":null,"funder_award_id":"R01 MH079068","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"},{"id":"https://openalex.org/G6649231326","display_name":"Text Mining Infrastructure for the Entire Biological Literature","funder_award_id":"0849977","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337346","display_name":"National Institute of Mental Health","ror":"https://ror.org/04xeg9z08"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2166633748.pdf","grobid_xml":"https://content.openalex.org/works/W2166633748.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W136741500","https://openalex.org/W1528012351","https://openalex.org/W1559499673","https://openalex.org/W1603229901","https://openalex.org/W1606489140","https://openalex.org/W1887406349","https://openalex.org/W1976097579","https://openalex.org/W2044420612","https://openalex.org/W2064354603","https://openalex.org/W2067522876","https://openalex.org/W2074231493","https://openalex.org/W2075322787","https://openalex.org/W2097056536","https://openalex.org/W2101727078","https://openalex.org/W2103308144","https://openalex.org/W2110279753","https://openalex.org/W2112543617","https://openalex.org/W2113733257","https://openalex.org/W2114361266","https://openalex.org/W2114702301","https://openalex.org/W2116502002","https://openalex.org/W2120686295","https://openalex.org/W2127555854","https://openalex.org/W2129113459","https://openalex.org/W2130930065","https://openalex.org/W2133993935","https://openalex.org/W2134533274","https://openalex.org/W2147880316","https://openalex.org/W2150652226","https://openalex.org/W2153554054","https://openalex.org/W2168598710","https://openalex.org/W2404602200","https://openalex.org/W2911441344","https://openalex.org/W2912026815","https://openalex.org/W2913978757","https://openalex.org/W3142746689"],"related_works":["https://openalex.org/W1901649692","https://openalex.org/W2368651715","https://openalex.org/W2994098660","https://openalex.org/W1625494842","https://openalex.org/W4378603571","https://openalex.org/W1663435917","https://openalex.org/W4384067529","https://openalex.org/W2997873848","https://openalex.org/W2604161433","https://openalex.org/W4320234404"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,17,120,156,329],"Portable":[2],"Document":[3],"Format":[4],"(PDF)":[5],"is":[6,134,317,334],"the":[7,60,89,126,130,199,204,244,247,259,262,268,271,286,290,332],"most":[8],"commonly":[9],"used":[10,251,294],"file":[11],"format":[12],"for":[13,37,79,139,306,321],"online":[14],"scientific":[15,327],"publications.":[16],"absence":[18],"of":[19,39,71,76,93,129,177,206,243,246,261,275,285,313,331],"effective":[20],"means":[21],"to":[22,67,172,267,295],"extract":[23,296],"text":[24,41,72,82,100,166,182,195,207,219,263,269,287,297,324],"from":[25,73,102,208,270,298,325],"these":[26],"PDF":[27,62,74],"files":[28,75],"in":[29,81,159,198,203,252],"a":[30,34,137,160,188],"layout-aware":[31],"manner":[32],"presents":[33],"significant":[35],"challenge":[36],"developers":[38],"biomedical":[40],"mining":[42,83],"or":[43],"biocuration":[44],"informatics":[45],"systems":[46],"that":[47,98,116,147,214,284],"use":[48,80],"published":[49],"literature":[50],"as":[51,136,152],"an":[52,94,241,318],"information":[53],"source.":[54],"In":[55],"this":[56,281],"paper":[57,87],"we":[58,256,301],"introduce":[59],"'Layout-Aware":[61],"Text":[63],"Extraction'":[64],"(LA-PDFText)":[65],"system":[66,97,122,157,216,308,333],"facilitate":[68],"accurate":[69],"extraction":[70,145,205],"research":[77,105,131],"articles":[78,106,132],"applications.":[84],"RESULTS:":[85],"Our":[86],"describes":[88],"construction":[90],"and":[91,107,133,154,174,191,221,234,309],"performance":[92],"open":[95],"source":[96],"extracts":[99],"blocks":[101,167,176,183,196,220],"PDF-formatted":[103],"full-text":[104,326],"classifies":[108],"them":[109,223],"into":[110,142,184,224],"logical":[111],"units":[112],"based":[113],"on":[114,125],"rules":[115],"characterize":[117],"specific":[118],"sections.":[119],"LA-PDFText":[121,266,316],"focuses":[123],"only":[124],"textual":[127],"content":[128],"meant":[135],"baseline":[138],"further":[140,311],"experiments":[141],"more":[143],"advanced":[144],"methods":[146],"handle":[148],"multi-modal":[149],"content,":[150],"such":[151],"images":[153],"graphs.":[155],"works":[158],"three-stage":[161],"process:":[162],"(1)":[163],"Detecting":[164],"contiguous":[165,178],"using":[168,187],"spatial":[169],"layout":[170],"processing":[171],"locate":[173],"identify":[175,218,310],"text,":[179],"(2)":[180],"Classifying":[181],"rhetorical":[185,225],"categories":[186,226],"rule-based":[189],"method":[190],"(3)":[192],"Stitching":[193],"classified":[194],"together":[197],"correct":[200],"order":[201],"resulting":[202],"section-wise":[209],"grouped":[210],"blocks.":[211],"We":[212,238,278],"show":[213],"our":[215,307],"can":[217],"classify":[222],"with":[227,283],"Precision1":[228],"=":[229,232,236],"0.96%":[230],"Recall":[231],"0.89%":[233],"F1":[235],"0.91%.":[237],"also":[239],"present":[240],"evaluation":[242],"accuracy":[245,260,282],"block":[248],"detection":[249],"algorithm":[250],"step":[253],"2.":[254],"Additionally,":[255],"have":[257],"compared":[258,280],"extracted":[264,288],"by":[265,289],"Open":[272],"Access":[273],"subset":[274],"PubMed":[276],"Central.":[277],"then":[279],"PDF2Text":[291],"system,":[292],"2commonly":[293],"PDF.":[299],"Finally,":[300],"discuss":[302],"preliminary":[303],"error":[304],"analysis":[305],"areas":[312],"improvement.":[314],"CONCLUSIONS:":[315],"open-source":[319],"tool":[320],"accurately":[322],"extracting":[323],"articles.":[328],"release":[330],"available":[335],"at":[336],"http://code.google.com/p/lapdftext/.":[337]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
