乐胖代购免代理版

{"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","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/3441580"},"language":"en","primary_location":{"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_indexed_in_scopus":false,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","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":"funder","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"],"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":"middle","author":{"id":"https://openalex.org/A5042684601","display_name":"Abhishek Patnia","orcid":null},"institutions":[{"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"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"funder","lineage":["https://openalex.org/I1174212"]}],"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"],"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/I4210164117","https://openalex.org/I1174212"]}]},{"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":"funder","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"],"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":"funder","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"],"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"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112629679"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":2.297,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":118,"citation_normalized_percentile":{"value":0.999986,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"7","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9984,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9984,"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"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9909,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9879,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8477143},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6925429},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.56927466},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.47553968},{"id":"https://openalex.org/C66945725","wikidata":"https://www.wikidata.org/wiki/Q18388823","display_name":"Text graph","level":3,"score":0.4453703},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4389193},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39351112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3345608},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.19238684},{"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":[{"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_indexed_in_scopus":false,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://europepmc.org/articles/pmc3441580","pdf_url":"https://europepmc.org/articles/pmc3441580?pdf=render","source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":["European Bioinformatics Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3441580","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_indexed_in_scopus":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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"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_indexed_in_scopus":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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"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_indexed_in_scopus":false,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.58}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":35,"referenced_works":["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/W4384067529","https://openalex.org/W4378603571","https://openalex.org/W4320234404","https://openalex.org/W2997873848","https://openalex.org/W2994098660","https://openalex.org/W2604161433","https://openalex.org/W2368651715","https://openalex.org/W1901649692","https://openalex.org/W1663435917","https://openalex.org/W1625494842"],"abstract_inverted_index":{"The":[0,16,117,153,324],"Portable":[1],"Document":[2],"Format":[3],"(PDF)":[4],"is":[5,131,312,329],"the":[6,59,86,123,127,196,201,241,244,256,259,265,268,283,287,327],"most":[7],"commonly":[8],"used":[9,248,291],"file":[10],"format":[11],"for":[12,36,78,136,303,316],"online":[13],"scientific":[14,322],"publications.":[15],"absence":[17],"of":[18,38,70,75,90,126,174,203,240,243,258,272,282,310,326],"effective":[19],"means":[20],"to":[21,66,169,264,292],"extract":[22,293],"text":[23,40,71,81,97,163,179,192,204,216,260,266,284,294,319],"from":[24,72,99,205,267,295,320],"these":[25],"PDF":[26,61,73],"files":[27,74],"in":[28,80,156,195,200,249],"a":[29,33,134,157,185],"layout-aware":[30],"manner":[31],"presents":[32],"significant":[34],"challenge":[35],"developers":[37],"biomedical":[39],"mining":[41,82],"or":[42],"biocuration":[43],"informatics":[44],"systems":[45],"that":[46,95,113,144,211,281],"use":[47,79],"published":[48],"literature":[49],"as":[50,133,149],"an":[51,91,238,313],"information":[52],"source.":[53],"In":[54],"this":[55,278],"paper":[56,84],"we":[57,253,298],"introduce":[58],"'Layout-Aware":[60],"Text":[62],"Extraction'":[63],"(LA-PDFText)":[64],"system":[65,94,119,154,213,305,328],"facilitate":[67],"accurate":[68],"extraction":[69,142,202],"research":[76,102,128],"articles":[77,103,129],"applications.Our":[83],"describes":[85],"construction":[87],"and":[88,104,130,151,171,188,218,231,306],"performance":[89],"open":[92],"source":[93],"extracts":[96],"blocks":[98,164,173,180,193,217],"PDF-formatted":[100],"full-text":[101,321],"classifies":[105],"them":[106,220],"into":[107,139,181,221],"logical":[108],"units":[109],"based":[110],"on":[111,122],"rules":[112],"characterize":[114],"specific":[115],"sections.":[116],"LA-PDFText":[118,263],"focuses":[120],"only":[121],"textual":[124],"content":[125],"meant":[132],"baseline":[135],"further":[137,308],"experiments":[138],"more":[140],"advanced":[141],"methods":[143],"handle":[145],"multi-modal":[146],"content,":[147],"such":[148],"images":[150],"graphs.":[152],"works":[155],"three-stage":[158],"process:":[159],"(1)":[160],"Detecting":[161],"contiguous":[162,175],"using":[165,184],"spatial":[166],"layout":[167],"processing":[168],"locate":[170],"identify":[172,215,307],"text,":[176],"(2)":[177],"Classifying":[178],"rhetorical":[182,222],"categories":[183,223],"rule-based":[186],"method":[187],"(3)":[189],"Stitching":[190],"classified":[191],"together":[194],"correct":[197],"order":[198],"resulting":[199],"section-wise":[206],"grouped":[207],"blocks.":[208],"We":[209,235,275],"show":[210],"our":[212,304],"can":[214],"classify":[219],"with":[224,280],"Precision1":[225],"=":[226,229,233],"0.96%":[227],"Recall":[228],"0.89%":[230],"F1":[232],"0.91%.":[234],"also":[236],"present":[237],"evaluation":[239],"accuracy":[242,257,279],"block":[245],"detection":[246],"algorithm":[247],"step":[250],"2.":[251],"Additionally,":[252],"have":[254],"compared":[255,277],"extracted":[261,285],"by":[262,286],"Open":[269],"Access":[270],"subset":[271],"PubMed":[273],"Central.":[274],"then":[276],"PDF2Text":[288],"system,":[289],"2commonly":[290],"PDF.":[296],"Finally,":[297],"discuss":[299],"preliminary":[300],"error":[301],"analysis":[302],"areas":[309],"improvement.LA-PDFText":[311],"open-source":[314],"tool":[315],"accurately":[317],"extracting":[318],"articles.":[323],"release":[325],"available":[330],"at":[331],"http://code.google.com/p/lapdftext/.":[332]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2166633748","counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":9},{"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":"2025-03-01T15:39:13.129046","created_date":"2016-06-24"}