{"id":"https://openalex.org/W1990423373","doi":"https://doi.org/10.1145/1739041.1739047","title":"Beyond pages","display_name":"Beyond pages","publication_year":2010,"publication_date":"2010-03-16","ids":{"openalex":"https://openalex.org/W1990423373","doi":"https://doi.org/10.1145/1739041.1739047","mag":"1990423373"},"language":"en","primary_location":{"id":"doi:10.1145/1739041.1739047","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1739041.1739047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Extending Database Technology","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100613252","display_name":"Tao Cheng","orcid":"https://orcid.org/0000-0002-4184-0730"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Cheng","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL","[University of Illinois at Urbana-Champaign,Urbana,IL]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,Urbana,IL]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101880377","display_name":"Kevin Chen\u2013Chuan Chang","orcid":"https://orcid.org/0000-0003-0997-6803"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Chen-Chuan Chang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL","[University of Illinois at Urbana-Champaign,Urbana,IL]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,Urbana,IL]","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":2.7247,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.91374443,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"15","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9984999895095825,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9984999895095825,"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/T11719","display_name":"Data Quality and Management","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"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":0.8595893979072571},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7975711226463318},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7087308168411255},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.684650182723999},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5868253111839294},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.48490196466445923},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42715588212013245},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34084612131118774},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1439671516418457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8595893979072571},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7975711226463318},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7087308168411255},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.684650182723999},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5868253111839294},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.48490196466445923},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42715588212013245},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34084612131118774},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1439671516418457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1739041.1739047","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1739041.1739047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Extending Database Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W122707235","https://openalex.org/W136059505","https://openalex.org/W167355512","https://openalex.org/W1604957788","https://openalex.org/W1607983314","https://openalex.org/W1896126460","https://openalex.org/W1977841655","https://openalex.org/W1981732427","https://openalex.org/W2007683451","https://openalex.org/W2015556048","https://openalex.org/W2037313714","https://openalex.org/W2055354597","https://openalex.org/W2064784316","https://openalex.org/W2076471773","https://openalex.org/W2082626166","https://openalex.org/W2093698835","https://openalex.org/W2115461474","https://openalex.org/W2115758952","https://openalex.org/W2116066543","https://openalex.org/W2116504754","https://openalex.org/W2122265344","https://openalex.org/W2124044117","https://openalex.org/W2124520756","https://openalex.org/W2130766266","https://openalex.org/W2135050452","https://openalex.org/W2146361824","https://openalex.org/W2154148563","https://openalex.org/W2168160104","https://openalex.org/W2296730655","https://openalex.org/W2744548668","https://openalex.org/W6605561650","https://openalex.org/W6677692869","https://openalex.org/W6684931624"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W4237510188","https://openalex.org/W2130160813","https://openalex.org/W2054476758","https://openalex.org/W2350613701","https://openalex.org/W2130597667"],"abstract_inverted_index":{"Entity":[0],"search,":[1],"a":[2,50,71,74],"significant":[3],"departure":[4],"from":[5],"page-based":[6],"retrieval,":[7],"finds":[8],"data,":[9],"i.e.,":[10],"entities,":[11],"embedded":[12],"in":[13,90],"documents":[14],"directly":[15],"and":[16,27,44,56,61,82],"holistically":[17],"across":[18],"the":[19,29,37,109],"whole":[20],"collection.":[21],"This":[22],"paper":[23],"aims":[24],"at":[25],"distilling":[26],"abstracting":[28],"essential":[30],"computation":[31],"requirements":[32],"of":[33,40,98,105],"entity":[34,45,85],"search.":[35],"From":[36],"dual":[38],"views":[39],"reasoning--entity":[41],"as":[42,46],"input":[43],"output,":[47],"we":[48],"propose":[49],"dual-inversion":[51],"framework,":[52],"with":[53,79,112],"two":[54,91],"indexing":[55],"partition":[57],"schemes,":[58],"towards":[59],"efficient":[60],"scalable":[62],"query":[63],"processing.":[64],"We":[65],"systematically":[66],"evaluate":[67],"our":[68,96],"framework":[69],"using":[70],"prototype":[72],"over":[73,83,108],"3TB":[75],"real":[76],"Web":[77],"corpus":[78],"150M":[80],"pages":[81],"20":[84],"types":[86],"extracted.":[87],"Our":[88],"experiments":[89],"concrete":[92],"application":[93],"settings":[94],"show":[95],"techniques":[97],"on":[99],"average,":[100],"2":[101],"to":[102],"4":[103],"orders":[104],"magnitude":[106],"speed-up,":[107],"keyword-based":[110],"baseline,":[111],"reasonable":[113],"space":[114],"overhead.":[115]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2016-06-24T00:00:00"}
