{"id":"https://openalex.org/W2105680621","doi":"https://doi.org/10.1109/icde.2010.5447751","title":"WikiAnalytics: Ad-hoc querying of highly heterogeneous structured data","display_name":"WikiAnalytics: Ad-hoc querying of highly heterogeneous structured data","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2105680621","doi":"https://doi.org/10.1109/icde.2010.5447751","mag":"2105680621"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2010.5447751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-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/A5003379355","display_name":"Andrey Balmin","orcid":"https://orcid.org/0000-0003-3034-6259"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrey Balmin","raw_affiliation_strings":["IBM Almaden Research Center, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074481302","display_name":"Emiran Curtmola","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emiran Curtmola","raw_affiliation_strings":["University of California, San Diego, USA",", UC San Diego, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":", UC San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003379355"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":1.4877,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83986793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1145","last_page":"1148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994000196456909,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9991999864578247,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"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":0.8808611631393433},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6972410082817078},{"id":"https://openalex.org/keywords/xquery","display_name":"XQuery","score":0.6249178647994995},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5512323975563049},{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.48277464509010315},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.4313563406467438},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4242561459541321},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.42365503311157227},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34786179661750793},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.251708060503006},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.21877384185791016},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21563240885734558},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1581573188304901},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.15425825119018555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8808611631393433},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6972410082817078},{"id":"https://openalex.org/C2780512708","wikidata":"https://www.wikidata.org/wiki/Q850661","display_name":"XQuery","level":4,"score":0.6249178647994995},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5512323975563049},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.48277464509010315},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4313563406467438},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4242561459541321},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.42365503311157227},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34786179661750793},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.251708060503006},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.21877384185791016},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21563240885734558},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1581573188304901},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.15425825119018555},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2010.5447751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.167.94","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.167.94","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://db.ucsd.edu/pubsFileFolder/336.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1503729935","https://openalex.org/W1513916588","https://openalex.org/W1522542599","https://openalex.org/W1989944922","https://openalex.org/W2098388305","https://openalex.org/W2105819430","https://openalex.org/W2108710846","https://openalex.org/W2113112851","https://openalex.org/W2121350579","https://openalex.org/W2128034913","https://openalex.org/W2137523786","https://openalex.org/W2148942721","https://openalex.org/W2157938327","https://openalex.org/W2169624745","https://openalex.org/W4255318870","https://openalex.org/W6630731242"],"related_works":["https://openalex.org/W2355446901","https://openalex.org/W2486756614","https://openalex.org/W2073024456","https://openalex.org/W4213327256","https://openalex.org/W2062115694","https://openalex.org/W2059040279","https://openalex.org/W1997305375","https://openalex.org/W4252166815","https://openalex.org/W4253215314","https://openalex.org/W158654455"],"abstract_inverted_index":{"Searching":[0],"and":[1,48,100,135,193,205,215,220],"extracting":[2],"meaningful":[3],"information":[4],"out":[5],"of":[6,18,98,108],"highly":[7],"heterogeneous":[8,109],"datasets":[9],"is":[10],"a":[11,16,104,144,178,191],"hot":[12],"topic":[13],"that":[14,124,137,180,196],"received":[15],"lot":[17],"attention.":[19],"However,":[20],"the":[21,55,80,126,139,155,163,166,172,185,198,202,223],"existing":[22,58],"solutions":[23,59],"are":[24,36,74],"based":[25,132,169],"on":[26,133,170],"either":[27],"rigid":[28],"complex":[29],"query":[30,140],"languages":[31],"(e.g.,":[32,218],"SQL,":[33],"XQuery/XPath)":[34],"which":[35,49,73,210],"hard":[37],"to":[38,77,95,115,161],"use":[39],"without":[40,44],"full":[41],"schema":[42],"knowledge,":[43],"an":[45,89],"expert":[46],"user,":[47],"require":[50],"up-front":[51],"data":[52,167,182],"integration.":[53],"At":[54],"other":[56],"extreme,":[57],"employ":[60],"keyword":[61],"search":[62,91,117,203],"queries":[63],"over":[64,70,149],"relational":[65],"databases,":[66],"as":[67,69],"well":[68],"semistructured":[71],"data,":[72],"too":[75],"imprecise":[76],"specify":[78],"exactly":[79],"user's":[81],"intent.":[82],"To":[83],"address":[84],"these":[85],"limitations,":[86],"we":[87,129],"propose":[88],"alternative":[90],"paradigm":[92],"in":[93,165],"order":[94],"derive":[96],"tables":[97],"precise":[99],"complete":[101],"results":[102,118,204],"from":[103,184],"very":[105],"sparse":[106],"set":[107],"records.":[110,127],"Our":[111],"approach":[112],"allows":[113],"users":[114],"disambiguate":[116],"by":[119],"navigation":[120],"along":[121],"conceptual":[122],"dimensions":[123],"describe":[125],"Therefore,":[128],"cluster":[130],"documents":[131,164],"fields":[134],"values":[136],"contain":[138],"keywords.":[141],"We":[142,175],"build":[143],"universal":[145],"navigational":[146],"lattice":[147],"(UNL)":[148],"all":[150,158],"such":[151],"discovered":[152],"clusters.":[153],"Conceptually,":[154],"UNL":[156],"encodes":[157],"possible":[159],"ways":[160],"group":[162],"corpus":[168],"where":[171],"keywords":[173],"hit.":[174],"describe,":[176],"WikiAnalytics,":[177],"system":[179],"facilitates":[181],"extraction":[183],"Wikipedia":[186],"infobox":[187],"collection.":[188],"WikiAnalytics":[189],"provides":[190],"dynamic":[192],"intuitive":[194],"interface":[195],"lets":[197],"average":[199],"user":[200],"explore":[201],"construct":[206],"homogeneous":[207],"structured":[208],"tables,":[209],"can":[211],"be":[212],"further":[213],"queried":[214],"mashed":[216],"up":[217],"filtered":[219],"aggregated)":[221],"using":[222],"conventional":[224],"tools.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}