{"id":"https://openalex.org/W2162235411","doi":"https://doi.org/10.1145/1807167.1807251","title":"Structured annotations of web queries","display_name":"Structured annotations of web queries","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2162235411","doi":"https://doi.org/10.1145/1807167.1807251","mag":"2162235411"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of 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/A5000660268","display_name":"Nikos Sarkas","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Nikos Sarkas","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112447002","display_name":"Stelios Paparizos","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stelios Paparizos","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066962453","display_name":"Panayiotis Tsaparas","orcid":"https://orcid.org/0000-0002-3490-1507"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panayiotis Tsaparas","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000660268"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":14.8866,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.99453899,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"771","last_page":"782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998000264167786,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991999864578247,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9987999796867371,"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":0.8890432119369507},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6756024360656738},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6284038424491882},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.5626921057701111},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5608002543449402},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.532677948474884},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.5108342170715332},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.49973464012145996},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.49323171377182007},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4492926001548767},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.44466084241867065},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.42670321464538574},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.38090288639068604},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.29914239048957825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25470373034477234},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23266446590423584},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.22373297810554504},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09934580326080322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8890432119369507},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6756024360656738},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6284038424491882},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.5626921057701111},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5608002543449402},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.532677948474884},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.5108342170715332},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.49973464012145996},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.49323171377182007},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4492926001548767},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.44466084241867065},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.42670321464538574},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.38090288639068604},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29914239048957825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25470373034477234},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23266446590423584},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.22373297810554504},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09934580326080322}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1807167.1807251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.359.9816","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.359.9816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.iitb.ac.in/~soumen/doc/www2013/QirWoo/SarkasPT2010QueryAnnotation.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.467.3968","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.467.3968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://linux7.papaki.gr:8443/sitepreview/http/paparizos.gr/resume/publications/annotationssigmod10.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.9420","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.9420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uoi.gr/%7Etsap/publications/annotations.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1506806321","https://openalex.org/W1512789266","https://openalex.org/W1663973292","https://openalex.org/W1973828215","https://openalex.org/W1981585544","https://openalex.org/W1989944922","https://openalex.org/W2000484009","https://openalex.org/W2007704545","https://openalex.org/W2008742021","https://openalex.org/W2020539781","https://openalex.org/W2048351742","https://openalex.org/W2081580037","https://openalex.org/W2087437797","https://openalex.org/W2094930182","https://openalex.org/W2103615139","https://openalex.org/W2108223890","https://openalex.org/W2124044117","https://openalex.org/W2125969310","https://openalex.org/W2126391456","https://openalex.org/W2143672210","https://openalex.org/W2146446188","https://openalex.org/W2148942721","https://openalex.org/W2151310484","https://openalex.org/W2167181946","https://openalex.org/W2171874178","https://openalex.org/W4212863985","https://openalex.org/W6629510986","https://openalex.org/W6650339521"],"related_works":["https://openalex.org/W2572349046","https://openalex.org/W2096359267","https://openalex.org/W2026738364","https://openalex.org/W2113390685","https://openalex.org/W3197639690","https://openalex.org/W2124814993","https://openalex.org/W8514837","https://openalex.org/W1981131819","https://openalex.org/W2017989738","https://openalex.org/W2186703450"],"abstract_inverted_index":{"Queries":[0],"asked":[1],"on":[2],"web":[3,38,48,59],"search":[4],"engines":[5],"often":[6],"target":[7],"structured":[8,56,81,92,147],"data,":[9],"such":[10,24],"as":[11,71],"commercial":[12],"products,":[13],"movie":[14],"showtimes,":[15],"or":[16],"airline":[17],"schedules.":[18],"However,":[19,113],"surfacing":[20],"relevant":[21],"results":[22],"from":[23],"data":[25,82,183],"is":[26],"a":[27,72,75,78,89,96,108,118,132,138,146,152],"highly":[28],"challenging":[29],"problem,":[30],"due":[31],"to":[32,77],"the":[33,37,41,126,143,167],"unstructured":[34],"language":[35],"of":[36,47,74,80,85,91,107,145],"queries,":[39],"and":[40,44,61,83,98,149,182,184],"imposing":[42],"scalability":[43],"speed":[45],"requirements":[46],"search.":[49],"In":[50],"this":[51,86],"paper,":[52],"we":[53,94,114,150],"discover":[54],"latent":[55],"semantics":[57],"in":[58],"queries":[60,181],"produce":[62],"Structured":[63],"Annotations":[64],"for":[65,102,117,125,141,155,169],"them.":[66],"We":[67,129,174],"consider":[68],"an":[69],"annotation":[70],"mapping":[73],"query":[76,109,120,159],"table":[79],"attributes":[84],"table.":[87],"Given":[88],"collection":[90],"tables,":[93],"present":[95,185],"fast":[97],"scalable":[99],"tagging":[100],"mechanism":[101],"obtaining":[103],"all":[104],"possible":[105],"annotations":[106],"over":[110],"these":[111],"tables.":[112],"observe":[115],"that":[116],"given":[119],"only":[121],"few":[122],"are":[123,163],"sensible":[124],"user":[127],"needs.":[128],"thus":[130],"propose":[131],"principled":[133],"probabilistic":[134],"scoring":[135],"mechanism,":[136],"using":[137,178],"generative":[139],"model,":[140],"assessing":[142],"likelihood":[144],"annotation,":[148],"define":[151],"dynamic":[153],"threshold":[154],"filtering":[156],"out":[157],"misinterpreted":[158],"annotations.":[160],"Our":[161],"techniques":[162,177],"completely":[164],"unsupervised,":[165],"obviating":[166],"need":[168],"costly":[170],"manual":[171],"labeling":[172],"effort.":[173],"evaluated":[175],"our":[176],"real":[179],"world":[180],"promising":[186],"experimental":[187],"results.":[188]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":18},{"year":2012,"cited_by_count":14}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}