{"id":"https://openalex.org/W2105524250","doi":"https://doi.org/10.1145/1935826.1935912","title":"Learning similarity function for rare queries","display_name":"Learning similarity function for rare queries","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W2105524250","doi":"https://doi.org/10.1145/1935826.1935912","mag":"2105524250"},"language":"en","primary_location":{"id":"doi:10.1145/1935826.1935912","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","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/A5102861619","display_name":"Jingfang Xu","orcid":"https://orcid.org/0000-0003-3699-7116"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingfang Xu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111526267","display_name":"Gu Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gu Xu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":3.0912,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.9401853,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"615","last_page":"624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9962999820709229,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8010214567184448},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.7237610220909119},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.670352041721344},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6590449810028076},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6039384603500366},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.5687021613121033},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.5597124099731445},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5449378490447998},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.47476935386657715},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.47467827796936035},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4668971002101898},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.4666927456855774},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46309423446655273},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4342949390411377},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4342103600502014},{"id":"https://openalex.org/keywords/spatial-query","display_name":"Spatial query","score":0.4331800043582916},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.4245082139968872},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4065050780773163},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.26046204566955566},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.19786807894706726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17691448330879211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010214567184448},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.7237610220909119},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.670352041721344},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6590449810028076},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6039384603500366},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.5687021613121033},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.5597124099731445},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5449378490447998},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.47476935386657715},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.47467827796936035},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4668971002101898},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.4666927456855774},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46309423446655273},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4342949390411377},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4342103600502014},{"id":"https://openalex.org/C172722865","wikidata":"https://www.wikidata.org/wiki/Q2302053","display_name":"Spatial query","level":5,"score":0.4331800043582916},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.4245082139968872},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4065050780773163},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.26046204566955566},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.19786807894706726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17691448330879211},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1935826.1935912","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","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":49,"referenced_works":["https://openalex.org/W1480643256","https://openalex.org/W1496731309","https://openalex.org/W1528544837","https://openalex.org/W1529878332","https://openalex.org/W1605350824","https://openalex.org/W1646006088","https://openalex.org/W1847544500","https://openalex.org/W1902364784","https://openalex.org/W1962648552","https://openalex.org/W1972645849","https://openalex.org/W1973867972","https://openalex.org/W1979459060","https://openalex.org/W2001306626","https://openalex.org/W2012833704","https://openalex.org/W2014987111","https://openalex.org/W2061296752","https://openalex.org/W2098326081","https://openalex.org/W2098876286","https://openalex.org/W2100507040","https://openalex.org/W2104752854","https://openalex.org/W2105106523","https://openalex.org/W2117154949","https://openalex.org/W2118840614","https://openalex.org/W2118979615","https://openalex.org/W2129271949","https://openalex.org/W2129921015","https://openalex.org/W2130556178","https://openalex.org/W2132555912","https://openalex.org/W2139273454","https://openalex.org/W2144882256","https://openalex.org/W2147152072","https://openalex.org/W2147717514","https://openalex.org/W2153190022","https://openalex.org/W2154347386","https://openalex.org/W2154628803","https://openalex.org/W2159788726","https://openalex.org/W2160555926","https://openalex.org/W2161443453","https://openalex.org/W2162006472","https://openalex.org/W2169495281","https://openalex.org/W2170741935","https://openalex.org/W2207050819","https://openalex.org/W2212057763","https://openalex.org/W2215874560","https://openalex.org/W2219977633","https://openalex.org/W2249820515","https://openalex.org/W2403299630","https://openalex.org/W4231856373","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2179956029","https://openalex.org/W4379390531","https://openalex.org/W2371740287","https://openalex.org/W2128834514","https://openalex.org/W2395027054","https://openalex.org/W1533255077","https://openalex.org/W906795786","https://openalex.org/W227397245","https://openalex.org/W2110065340","https://openalex.org/W3162539059"],"abstract_inverted_index":{"The":[0],"key":[1],"element":[2],"of":[3,13,139,152,166],"many":[4,27],"query":[5,19,21,24,33,56,145,167],"processing":[6],"tasks":[7],"can":[8,161,193],"be":[9],"formalized":[10,114],"as":[11,45,115],"calculation":[12,169],"similarities":[14,92],"between":[15,93],"queries.":[16,42,94,177],"These":[17],"include":[18],"suggestion,":[20],"reformulation,":[22],"and":[23,59,85,119,173],"expansion.":[25],"Although":[26],"methods":[28],"have":[29],"been":[30],"proposed":[31,154],"for":[32,136,170],"similarity":[34,57,87,100,168],"calculation,":[35,58],"they":[36],"could":[37],"perform":[38],"poorly":[39],"on":[40],"rare":[41,55,171],"As":[43,178],"far":[44],"we":[46,68,73,96,131,181],"know,":[47],"there":[48],"was":[49],"no":[50],"previous":[51],"work":[52],"particularly":[53],"about":[54],"this":[60,65],"paper":[61],"tries":[62],"to":[63,78,89,126],"study":[64],"problem.":[66],"Specifically,":[67],"address":[69],"three":[70],"problems.":[71],"Firstly,":[72],"define":[74],"an":[75,116,179],"n-gram":[76],"space":[77],"represent":[79],"queries":[80,141,172,188],"with":[81],"their":[82],"own":[83],"content":[84],"a":[86,120,143],"function":[88,101],"measure":[90],"the":[91,99,104,150,153,164,186],"Secondly,":[95],"propose":[97],"learning":[98,122],"by":[102,156,190],"leveraging":[103],"training":[105],"data":[106],"derived":[107],"from":[108,142],"user":[109],"behavior":[110],"data.":[111],"This":[112],"is":[113,124],"optimization":[117],"problem":[118],"metric":[121],"approach":[123,155],"employed":[125],"solve":[127],"it":[128],"efficiently.":[129],"Finally,":[130],"exploit":[132],"locality":[133],"sensitive":[134],"hashing":[135],"efficient":[137],"retrieval":[138],"similar":[140,176,187],"large":[144],"repository.":[146],"We":[147],"experimentally":[148,183],"verified":[149],"effectiveness":[151],"showing":[157],"that":[158,185],"our":[159,191],"method":[160,192],"indeed":[162],"enhance":[163],"accuracy":[165],"efficiently":[174],"retrieve":[175],"application,":[180],"also":[182],"demonstrated":[184],"found":[189],"significantly":[194],"improve":[195],"search":[196],"relevance.":[197]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}