{"id":"https://openalex.org/W2325923789","doi":"https://doi.org/10.1145/2872427.2882975","title":"Discovering Structure in the Universe of Attribute Names","display_name":"Discovering Structure in the Universe of Attribute Names","publication_year":2016,"publication_date":"2016-04-11","ids":{"openalex":"https://openalex.org/W2325923789","doi":"https://doi.org/10.1145/2872427.2882975","mag":"2325923789"},"language":"en","primary_location":{"id":"doi:10.1145/2872427.2882975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2872427.2882975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Conference on World Wide Web","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/A5067621853","display_name":"Alon Halevy","orcid":"https://orcid.org/0000-0002-8717-7356"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alon Halevy","raw_affiliation_strings":["Recruit Institute of Technology, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Recruit Institute of Technology, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111383811","display_name":"Natalya F. Noy","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natalya Noy","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031035935","display_name":"Sunita Sarawagi","orcid":"https://orcid.org/0009-0005-9538-6616"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sunita Sarawagi","raw_affiliation_strings":["Google Research & IIT Bombay, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research & IIT Bombay, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012631773","display_name":"Steven Euijong Whang","orcid":"https://orcid.org/0000-0001-6419-931X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Euijong Whang","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047060039","display_name":"Xiao Yu","orcid":"https://orcid.org/0000-0002-4473-3068"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Yu","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"939","last_page":"949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8487910628318787},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6769002676010132},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5798363089561462},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5037979483604431},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4964194893836975},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4690972566604614},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4663834571838379},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4645492732524872},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36460986733436584},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12310251593589783},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08220979571342468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8487910628318787},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6769002676010132},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5798363089561462},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5037979483604431},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4964194893836975},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4690972566604614},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4663834571838379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4645492732524872},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36460986733436584},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12310251593589783},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08220979571342468},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2872427.2882975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2872427.2882975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W47977171","https://openalex.org/W90502410","https://openalex.org/W102708294","https://openalex.org/W145849181","https://openalex.org/W407632632","https://openalex.org/W592468124","https://openalex.org/W1483236033","https://openalex.org/W1508977358","https://openalex.org/W1527783480","https://openalex.org/W1593045043","https://openalex.org/W1662133657","https://openalex.org/W1759446372","https://openalex.org/W1969221592","https://openalex.org/W2002619677","https://openalex.org/W2068737686","https://openalex.org/W2081375810","https://openalex.org/W2094625154","https://openalex.org/W2094728533","https://openalex.org/W2105842272","https://openalex.org/W2115791615","https://openalex.org/W2123958887","https://openalex.org/W2126725946","https://openalex.org/W2127350043","https://openalex.org/W2127978399","https://openalex.org/W2129842875","https://openalex.org/W2133227149","https://openalex.org/W2134418889","https://openalex.org/W2138605095","https://openalex.org/W2151502664","https://openalex.org/W2151803977","https://openalex.org/W2152135319","https://openalex.org/W2153579005","https://openalex.org/W2160918952","https://openalex.org/W2167187514","https://openalex.org/W2252168718","https://openalex.org/W2252218921","https://openalex.org/W2300534015","https://openalex.org/W3010318089","https://openalex.org/W3126976873","https://openalex.org/W4399406577","https://openalex.org/W6610080458","https://openalex.org/W6677704767","https://openalex.org/W6698405968"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2357523926"],"abstract_inverted_index":{"Recently,":[0],"search":[1,66],"engines":[2,67],"have":[3,15,28],"invested":[4],"significant":[5],"effort":[6],"to":[7,48,53,60,69,85,136,147,190,198,217],"answering":[8],"entity--attribute":[9,71],"queries":[10,19],"from":[11,132,153,196],"structured":[12],"data,":[13],"but":[14],"focused":[16],"mostly":[17],"on":[18,89],"for":[20],"frequent":[21],"attributes.":[22,96],"In":[23],"parallel,":[24],"several":[25],"research":[26],"efforts":[27],"demonstrated":[29],"that":[30,44,64,162],"there":[31],"is":[32],"a":[33,115,121,150,154,167,178,204],"long":[34,91],"tail":[35,94],"of":[36,42,46,58,74,78,95,102,111,127,157,173,194,222],"attributes,":[37,80,129],"often":[38],"thousands":[39],"per":[40],"class":[41],"entities,":[43],"are":[45,51],"interest":[47],"users.":[49],"Researchers":[50],"beginning":[52],"leverage":[54],"these":[55],"new":[56,137],"collections":[57],"attributes":[59,105,135,172,195,221],"expand":[61,218],"the":[62,75,100,104,108,133,182,192],"ontologies":[63,219],"power":[65],"and":[68,92,123,214],"recognize":[70],"queries.":[72],"Because":[73],"sheer":[76],"number":[77],"potential":[79],"such":[81,149],"tasks":[82],"require":[83],"us":[84,189],"impose":[86],"some":[87],"structure":[88,110],"this":[90],"heavy":[93],"This":[97],"paper":[98,141],"introduces":[99],"problem":[101],"organizing":[103],"by":[106],"expressing":[107],"compositional":[109],"their":[112],"names":[113],"as":[114],"rule-based":[116],"grammar.":[117],"These":[118],"rules":[119],"offer":[120],"compact":[122],"rich":[124],"semantic":[125],"interpretation":[126],"multi-word":[128],"while":[130,176],"generalizing":[131],"observed":[134],"unseen":[138],"ones.":[139],"The":[140],"describes":[142],"an":[143,212],"unsupervised":[144],"learning":[145],"method":[146,164],"generate":[148],"grammar":[151,169,187],"automatically":[152],"large":[155],"set":[156],"attribute":[158,183],"names.":[159,184],"Experiments":[160],"show":[161],"our":[163,186,209],"can":[165],"discover":[166],"precise":[168],"over":[170,181],"100,000":[171],"{\\sc":[174],"Countries}":[175],"providing":[177],"40-fold":[179],"compaction":[180],"Furthermore,":[185],"enables":[188],"increase":[191],"precision":[193],"47\\%":[197],"more":[199],"than":[200],"90\\%":[201],"with":[202,220],"only":[203],"minimal":[205],"curation":[206],"effort.":[207],"Thus,":[208],"approach":[210],"provides":[211],"efficient":[213],"scalable":[215],"way":[216],"user":[223],"interest.":[224]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}