{"id":"https://openalex.org/W2400661088","doi":"https://doi.org/10.14778/2824032.2824058","title":"Extracting logical hierarchical structure of HTML documents based on headings","display_name":"Extracting logical hierarchical structure of HTML documents based on headings","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2400661088","doi":"https://doi.org/10.14778/2824032.2824058","mag":"2400661088"},"language":"en","primary_location":{"id":"doi:10.14778/2824032.2824058","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824058","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","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/A5112147297","display_name":"Tomohiro Manabe","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Manabe","raw_affiliation_strings":["Kyoto University, Sakyo, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103793743","display_name":"Keishi Tajima","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keishi Tajima","raw_affiliation_strings":["Kyoto University, Sakyo, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.4211,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97109041,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"8","issue":"12","first_page":"1606","last_page":"1617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9532999992370605,"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/T13976","display_name":"Web visibility and informetrics","score":0.9532999992370605,"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/computer-science","display_name":"Computer science","score":0.7484076023101807},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7093523144721985},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6455311179161072},{"id":"https://openalex.org/keywords/logical-conjunction","display_name":"Logical conjunction","score":0.4471283257007599},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44125303626060486},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.421800434589386},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3598365783691406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3325173854827881},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17875340580940247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484076023101807},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7093523144721985},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6455311179161072},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.4471283257007599},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44125303626060486},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.421800434589386},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3598365783691406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3325173854827881},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17875340580940247},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2824032.2824058","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824058","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W99921237","https://openalex.org/W1491206589","https://openalex.org/W1511676561","https://openalex.org/W1539890081","https://openalex.org/W1540618313","https://openalex.org/W1803802947","https://openalex.org/W1858341864","https://openalex.org/W1976022204","https://openalex.org/W1984130280","https://openalex.org/W1988926831","https://openalex.org/W2012575882","https://openalex.org/W2019264297","https://openalex.org/W2020254000","https://openalex.org/W2034607275","https://openalex.org/W2045717510","https://openalex.org/W2051097555","https://openalex.org/W2057017396","https://openalex.org/W2082884138","https://openalex.org/W2084358158","https://openalex.org/W2093752301","https://openalex.org/W2116771527","https://openalex.org/W2133669904","https://openalex.org/W2136783895","https://openalex.org/W2143309843","https://openalex.org/W2146486820","https://openalex.org/W2150290224","https://openalex.org/W2150721933","https://openalex.org/W2157316480","https://openalex.org/W2164777277","https://openalex.org/W2171364811","https://openalex.org/W2549918794","https://openalex.org/W6646212105","https://openalex.org/W6653392479","https://openalex.org/W6681480118","https://openalex.org/W6682150279"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"method":[3,106,124,131],"for":[4,111],"extracting":[5,112],"logical":[6,23,33,44],"hierarchical":[7,24,113,135],"structure":[8,14,34],"of":[9,35,63,71,84,96],"HTML":[10,16,36],"documents.":[11,37,56],"Because":[12],"mark-up":[13],"in":[15,54],"documents":[17],"does":[18],"not":[19,28,133],"necessarily":[20],"coincide":[21],"with":[22],"structure,":[25],"it":[26],"is":[27,52],"trivial":[29],"how":[30],"to":[31],"extract":[32],"Human":[38,57],"readers,":[39],"however,":[40],"easily":[41],"understand":[42],"their":[43,116,139],"structure.":[45],"The":[46],"key":[47],"information":[48],"used":[49],"by":[50],"them":[51],"headings":[53,66,76,83,95,114],"the":[55,60,69,72,85,89],"readers":[58],"exploit":[59],"following":[61],"properties":[62,110],"headings:":[64],"(1)":[65],"appear":[67],"at":[68],"beginning":[70],"corresponding":[73],"blocks,":[74],"(2)":[75],"are":[77,99],"given":[78,100],"prominent":[79,102],"visual":[80,91,103],"styles,":[81],"(3)":[82],"same":[86,90],"level":[87],"share":[88],"style,":[92],"and":[93,115],"(4)":[94],"higher":[97],"levels":[98],"more":[101],"styles.":[104],"Our":[105,119],"also":[107,138],"exploits":[108],"these":[109],"associated":[117,140],"blocks.":[118],"experiment":[120],"shows":[121],"that":[122],"our":[123,130],"outperforms":[125],"existing":[126],"methods.":[127],"In":[128],"addition,":[129],"extracts":[132],"only":[134],"blocks":[136],"but":[137],"headings.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}