{"id":"https://openalex.org/W2064354603","doi":"https://doi.org/10.4018/jdls.2010100101","title":"Logical Structure Recovery in Scholarly Articles with Rich Document Features","display_name":"Logical Structure Recovery in Scholarly Articles with Rich Document Features","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2064354603","doi":"https://doi.org/10.4018/jdls.2010100101","mag":"2064354603"},"language":"en","primary_location":{"id":"doi:10.4018/jdls.2010100101","is_oa":false,"landing_page_url":"https://doi.org/10.4018/jdls.2010100101","pdf_url":null,"source":{"id":"https://openalex.org/S143974849","display_name":"International Journal of Digital Library Systems","issn_l":"1947-9077","issn":["1947-9077","1947-9085"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Digital Library Systems","raw_type":"journal-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/A5078684067","display_name":"Minh-Thang Luong","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Minh-Thang Luong","raw_affiliation_strings":["National University of Singapore, Singapore","Nat. Univ. of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101965727","display_name":"Thuy Nguyen","orcid":"https://orcid.org/0000-0002-6283-7602"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Thuy Dung Nguyen","raw_affiliation_strings":["National University of Singapore, Singapore","Nat. Univ. of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066305082","display_name":"Min\u2010Yen Kan","orcid":"https://orcid.org/0000-0001-8507-3716"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Min-Yen Kan","raw_affiliation_strings":["National University of Singapore, Singapore","Nat. Univ. of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078684067"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":4.5258,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.95140011,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"1","issue":"4","first_page":"1","last_page":"23"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9957000017166138,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9926000237464905,"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":0.8033242225646973},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6838866472244263},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6761853098869324},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6431342959403992},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.5346490740776062},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5229619145393372},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.5013306140899658},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47945085167884827},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.46583905816078186},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46339231729507446},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.4520754814147949},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.41229143738746643},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4039337635040283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2287825047969818},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.1798364520072937},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11963573098182678},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08829325437545776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8033242225646973},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6838866472244263},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6761853098869324},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6431342959403992},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.5346490740776062},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5229619145393372},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.5013306140899658},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47945085167884827},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.46583905816078186},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46339231729507446},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.4520754814147949},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.41229143738746643},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4039337635040283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2287825047969818},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.1798364520072937},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11963573098182678},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08829325437545776},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.4018/jdls.2010100101","is_oa":false,"landing_page_url":"https://doi.org/10.4018/jdls.2010100101","pdf_url":null,"source":{"id":"https://openalex.org/S143974849","display_name":"International Journal of Digital Library Systems","issn_l":"1947-9077","issn":["1947-9077","1947-9085"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Digital Library Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.178.7521","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.178.7521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wing.comp.nus.edu.sg/parsCit/ijdls-SectLabel.pdf","raw_type":"text"},{"id":"pmh:oai:RePEc:igg:jdls00:v:1:y:2010:i:4:p:1-23","is_oa":false,"landing_page_url":"http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/jdls.2010100101","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W44107710","https://openalex.org/W1490343430","https://openalex.org/W1507630970","https://openalex.org/W1534730506","https://openalex.org/W1559499673","https://openalex.org/W1560013842","https://openalex.org/W1568339100","https://openalex.org/W1574901103","https://openalex.org/W1575936579","https://openalex.org/W1585694372","https://openalex.org/W1994471599","https://openalex.org/W2009570821","https://openalex.org/W2011296149","https://openalex.org/W2022322548","https://openalex.org/W2079525773","https://openalex.org/W2139120659","https://openalex.org/W2140479099","https://openalex.org/W2145130412","https://openalex.org/W2147880316","https://openalex.org/W2159164462","https://openalex.org/W2161197753","https://openalex.org/W2404602200"],"related_works":["https://openalex.org/W2573990671","https://openalex.org/W2000372441","https://openalex.org/W2096747878","https://openalex.org/W2244000356","https://openalex.org/W1971234693","https://openalex.org/W3046471831","https://openalex.org/W2744419436","https://openalex.org/W3021512437","https://openalex.org/W1969168333","https://openalex.org/W2784287639"],"abstract_inverted_index":{"Scholarly":[0],"digital":[1,141],"libraries":[2],"increasingly":[3],"provide":[4],"analytics":[5],"to":[6,21,44,70,85,149],"information":[7,13],"within":[8],"documents":[9],"themselves.":[10],"This":[11],"includes":[12,97],"about":[14],"the":[15,33,46,57,71,76,87,94,133],"logical":[16,47,119],"document":[17,51,95,137],"structure":[18,48,120],"of":[19,49,59,75,81,89,93,135],"use":[20,88,134],"downstream":[22],"components,":[23],"such":[24,104,115],"as":[25,105],"search,":[26],"navigation,":[27],"and":[28,108],"summarization.":[29],"In":[30],"this":[31,82,151],"paper,":[32],"authors":[34],"describe":[35],"SectLabel,":[36],"a":[37,50,78,90,123,129],"module":[38],"that":[39,96,113],"further":[40],"develops":[41],"existing":[42,53],"software":[43],"detect":[45],"from":[52,99,146],"PDF":[54],"files,":[55],"using":[56,114],"formalism":[58],"conditional":[60],"random":[61],"fields.":[62],"While":[63],"previous":[64],"work":[65,83],"has":[66],"assumed":[67],"access":[68,145],"only":[69],"raw":[72],"text":[73,109],"representation":[74,92],"document,":[77],"key":[79],"aspect":[80],"is":[84],"integrate":[86],"richer":[91,136],"features":[98,117],"optical":[100],"character":[101],"recognition":[102],"(OCR),":[103],"font":[106],"size":[107],"position.":[110],"Experiments":[111],"reveal":[112],"rich":[116],"improves":[118],"detection":[121],"by":[122],"significant":[124],"9":[125],"F1":[126],"points,":[127],"over":[128],"suitable":[130],"baseline,":[131],"motivating":[132],"representations":[138],"in":[139],"other":[140],"library":[142],"applications.":[143],"Request":[144],"your":[147],"librarian":[148],"read":[150],"article's":[152],"full":[153],"text.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
