{"id":"https://openalex.org/W2139259611","doi":"https://doi.org/10.14778/1687627.1687665","title":"A hierarchical approach to model web query interfaces for web source integration","display_name":"A hierarchical approach to model web query interfaces for web source integration","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2139259611","doi":"https://doi.org/10.14778/1687627.1687665","mag":"2139259611"},"language":"en","primary_location":{"id":"doi:10.14778/1687627.1687665","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687665","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/A5057346703","display_name":"Eduard Dragut","orcid":"https://orcid.org/0000-0002-3103-054X"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eduard C. Dragut","raw_affiliation_strings":["University of Illinois at Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083645268","display_name":"Thomas Kabisch","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Kabisch","raw_affiliation_strings":["Humboldt-Universit\u00e4t zu Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humboldt-Universit\u00e4t zu Berlin","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109181755","display_name":"Clement Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clement Yu","raw_affiliation_strings":["University of Illinois at Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055236937","display_name":"Ulf Leser","orcid":"https://orcid.org/0000-0003-2166-9582"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulf Leser","raw_affiliation_strings":["Humboldt-Universit\u00e4t zu Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humboldt-Universit\u00e4t zu Berlin","institution_ids":["https://openalex.org/I39343248"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":25.4567,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.99396243,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"2","issue":"1","first_page":"325","last_page":"336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9771999716758728,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.877692461013794},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.7413694858551025},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.6329375505447388},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5863252878189087},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5206633806228638},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4807855486869812},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4745415151119232},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.4704265594482422},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.44431963562965393},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.4286878705024719},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.4132389426231384},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25653740763664246},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.1645154058933258},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.10146400332450867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.877692461013794},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.7413694858551025},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.6329375505447388},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5863252878189087},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5206633806228638},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4807855486869812},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4745415151119232},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.4704265594482422},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.44431963562965393},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.4286878705024719},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.4132389426231384},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25653740763664246},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.1645154058933258},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.10146400332450867}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/1687627.1687665","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687665","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"},{"id":"pmh:oai:docs.lib.purdue.edu:ccpubs-1056","is_oa":false,"landing_page_url":"https://docs.lib.purdue.edu/ccpubs/46","pdf_url":null,"source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cyber Center Publications","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.4686","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.4686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/2/vldb09-360.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320875","display_name":"Deutscher Akademischer Austauschdienst","ror":"https://ror.org/039djdh30"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W127846897","https://openalex.org/W343945789","https://openalex.org/W1534024124","https://openalex.org/W1602176513","https://openalex.org/W1969831559","https://openalex.org/W1985079777","https://openalex.org/W1997868819","https://openalex.org/W2027780984","https://openalex.org/W2069388662","https://openalex.org/W2085433073","https://openalex.org/W2087846792","https://openalex.org/W2098016092","https://openalex.org/W2101610060","https://openalex.org/W2104448209","https://openalex.org/W2110034127","https://openalex.org/W2117058208","https://openalex.org/W2120642948","https://openalex.org/W2122604280","https://openalex.org/W2123853152","https://openalex.org/W2130760429","https://openalex.org/W2156543375","https://openalex.org/W2157060173","https://openalex.org/W2164896748","https://openalex.org/W2170188121","https://openalex.org/W3147052988"],"related_works":["https://openalex.org/W2350026801","https://openalex.org/W2363027842","https://openalex.org/W2366423674","https://openalex.org/W1601704076","https://openalex.org/W2372938158","https://openalex.org/W1531938654","https://openalex.org/W2354542834","https://openalex.org/W2035374497","https://openalex.org/W2171487998","https://openalex.org/W2139259611"],"abstract_inverted_index":{"Much":[0],"data":[1],"in":[2,207],"the":[3,14,19,58,70,82,112,131,159,180,190,197],"Web":[4,8,23,37,40,85,102,120,219],"is":[5,25,57,144,156,169],"hidden":[6],"behind":[7],"query":[9,62,86,91,103,167,202],"interfaces.":[10,32,49,87],"In":[11,96],"most":[12,132],"cases":[13],"only":[15],"means":[16],"to":[17,54],"\"surface\"":[18],"content":[20],"of":[21,47,61,72,75,84,115,129,165,192],"a":[22,73,101,119,166],"database":[24,41],"by":[26,171],"formulating":[27],"complex":[28],"queries":[29],"on":[30,200,204],"such":[31,34],"Applications":[33],"as":[35,209],"Deep":[36,218],"crawling":[38],"and":[39,111,138],"integration":[42,185],"require":[43],"an":[44,51,65,184],"automatic":[45,59],"usage":[46],"these":[48,116,174],"Therefore,":[50],"important":[52],"problem":[53,182],"be":[55],"addressed":[56],"extraction":[60,105,181],"interfaces":[63,92,203,220],"into":[64,93,125,183],"appropriate":[66],"model.":[67],"We":[68],"hypothesize":[69],"existence":[71],"set":[74],"domain-independent":[76],"\"commonsense":[77],"design":[78],"rules\"":[79],"that":[80],"guides":[81],"creation":[83],"These":[88],"rules":[89],"transform":[90],"schema":[94],"trees.":[95,176],"this":[97],"paper":[98],"we":[99,178],"describe":[100],"interface":[104,168],"algorithm,":[106],"which":[107,130],"combines":[108],"HTML":[109],"tokens":[110,117,137,148],"geometric":[113,151],"layout":[114],"within":[118],"page.":[121],"Tokens":[122],"are":[123,135],"classified":[124],"several":[126],"classes":[127],"out":[128],"significant":[133],"ones":[134],"text":[136,147],"field":[139,160],"tokens.":[140,161],"A":[141],"tree":[142,154],"structure":[143,155],"derived":[145,157],"for":[146,158],"using":[149],"their":[150],"layout.":[152],"Another":[153],"The":[162],"hierarchical":[163],"representation":[164],"obtained":[170],"iteratively":[172],"merging":[173],"two":[175],"Thus,":[177],"convert":[179],"problem.":[186],"Our":[187],"experiments":[188],"show":[189],"promise":[191],"our":[193],"algorithm:":[194],"it":[195],"outperforms":[196],"previous":[198],"approaches":[199],"extracting":[201],"about":[205],"6.5%":[206],"accuracy":[208],"evaluated":[210],"over":[211],"three":[212],"corpora":[213],"with":[214],"more":[215],"than":[216],"500":[217],"from":[221],"15":[222],"different":[223],"domains.":[224]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":15}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
