{"id":"https://openalex.org/W2029960028","doi":"https://doi.org/10.1145/2254736.2254738","title":"Towards a high quality and web-scalable table search engine","display_name":"Towards a high quality and web-scalable table search engine","publication_year":2012,"publication_date":"2012-05-20","ids":{"openalex":"https://openalex.org/W2029960028","doi":"https://doi.org/10.1145/2254736.2254738","mag":"2029960028"},"language":"en","primary_location":{"id":"doi:10.1145/2254736.2254738","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2254736.2254738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third International Workshop on Keyword Search on Structured Data","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/A5043275971","display_name":"Cong Yu","orcid":"https://orcid.org/0000-0001-7331-2345"},"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":true,"raw_author_name":"Cong Yu","raw_affiliation_strings":["Google Research, New York, NY"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043275971"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.15036577,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80824441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.996399998664856,"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":0.996399998664856,"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/T11106","display_name":"Data Management and Algorithms","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9818999767303467,"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":0.824946403503418},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5960074663162231},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.59080570936203},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5885288715362549},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5688525438308716},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5313915014266968},{"id":"https://openalex.org/keywords/search-analytics","display_name":"Search analytics","score":0.5311735272407532},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4879972040653229},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.4747462868690491},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4439558982849121},{"id":"https://openalex.org/keywords/search-engine-optimization","display_name":"Search engine optimization","score":0.4433749318122864},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.42307135462760925},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41239866614341736},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.29820090532302856},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.29350119829177856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824946403503418},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5960074663162231},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.59080570936203},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5885288715362549},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5688525438308716},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5313915014266968},{"id":"https://openalex.org/C14838553","wikidata":"https://www.wikidata.org/wiki/Q7441639","display_name":"Search analytics","level":4,"score":0.5311735272407532},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4879972040653229},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.4747462868690491},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4439558982849121},{"id":"https://openalex.org/C178218473","wikidata":"https://www.wikidata.org/wiki/Q180711","display_name":"Search engine optimization","level":3,"score":0.4433749318122864},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.42307135462760925},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41239866614341736},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.29820090532302856},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.29350119829177856},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2254736.2254738","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2254736.2254738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third International Workshop on Keyword Search on Structured Data","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2113184419","https://openalex.org/W2980544443","https://openalex.org/W4254300012","https://openalex.org/W1999548128","https://openalex.org/W2419328283","https://openalex.org/W1770021664","https://openalex.org/W2389041382","https://openalex.org/W2964491004","https://openalex.org/W2223855511","https://openalex.org/W2296228743"],"abstract_inverted_index":{"For":[0],"over":[1,35,100,126],"a":[2,4,107,166],"decade,":[3],"large":[5],"number":[6],"of":[7,53,56,68,110],"studies":[8],"have":[9,132],"explored":[10],"efficient":[11],"mechanisms":[12],"for":[13],"finding":[14],"relevant":[15],"information":[16],"from":[17,116,124],"structured":[18,36,57,71,101,171,182],"sources":[19],"such":[20],"as":[21,120,122],"relational,":[22],"semi-structured,":[23],"and":[24,48,142,169],"graph":[25],"databases.":[26],"While":[27],"successful":[28],"in":[29,145],"its":[30,117],"own":[31],"right,":[32],"keyword":[33,98],"search":[34,99,130,159,173],"data":[37,58,72,76,102,172,183],"has":[38],"yet":[39],"to":[40],"gain":[41],"wide":[42],"spread":[43],"adoption":[44],"on":[45,59,103,180,184],"the":[46,54,60,64,90,104,129,157,185],"Web,":[47],"it":[49],"is":[50,96],"not":[51],"because":[52],"lack":[55],"Web.":[61,186],"In":[62,134,152],"fact,":[63],"Web":[65,105],"offers":[66],"orders":[67],"magnitude":[69],"more":[70],"than":[73],"any":[74],"offline":[75],"source:":[77],"14":[78],"billions":[79],"tables":[80],"can":[81],"be":[82],"gathered":[83],"just":[84],"by":[85],"considering":[86],"page":[87],"content":[88],"between":[89],"table":[91,158],"tags.":[92],"The":[93],"main":[94],"reason":[95],"that":[97,112],"presents":[106],"unique":[108],"set":[109],"challenges":[111,141],"are":[113],"quite":[114],"different":[115,123],"non-Web":[118],"counterparts,":[119],"well":[121],"searching":[125],"documents":[127],"(where":[128],"engines":[131],"excelled).":[133],"this":[135],"talk,":[136],"I":[137,154],"will":[138,155],"discuss":[139],"those":[140],"our":[143,161,177],"approaches":[144],"addressing":[146],"them":[147],"at":[148],"Google's":[149],"WebTables":[150],"project.":[151],"particular,":[153],"present":[156],"engine,":[160,174],"initial":[162],"effort":[163],"toward":[164],"building":[165],"high":[167],"quality":[168],"scalable":[170],"along":[175],"with":[176],"other":[178],"efforts":[179],"managing":[181]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
