{"id":"https://openalex.org/W2004134257","doi":"https://doi.org/10.1145/1031171.1031240","title":"Learning similarity measures in non-orthogonal space","display_name":"Learning similarity measures in non-orthogonal space","publication_year":2004,"publication_date":"2004-11-13","ids":{"openalex":"https://openalex.org/W2004134257","doi":"https://doi.org/10.1145/1031171.1031240","mag":"2004134257"},"language":"en","primary_location":{"id":"doi:10.1145/1031171.1031240","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031171.1031240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the thirteenth ACM international conference on Information and knowledge management","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/A5101683584","display_name":"Ning Liu","orcid":"https://orcid.org/0009-0008-5231-1835"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Liu","raw_affiliation_strings":["Tsinghua University, Beijing, P.R. China","TsingHua University, Beijing, P.R. China#TAB#"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, P.R. China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"TsingHua University, Beijing, P.R. China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053072892","display_name":"Benyu Zhang","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"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Benyu Zhang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P.R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030330619","display_name":"Jun Yan","orcid":"https://orcid.org/0000-0003-2497-5518"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yan","raw_affiliation_strings":["Peking University, Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, P.R. China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636286","display_name":"Qiang Yang","orcid":"https://orcid.org/0000-0001-5059-8360"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong","Hong Kong University of Science and Technology; Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University of Science and Technology; Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381753","display_name":"Shuicheng Yan","orcid":"https://orcid.org/0000-0001-8906-3777"},"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"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P.R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370684","display_name":"Zheng Chen","orcid":"https://orcid.org/0000-0002-9654-0997"},"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"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Zheng Chen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P.R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102215816","display_name":"Fengshan Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengshan Bai","raw_affiliation_strings":["Tsinghua University, Beijing, P.R. China","TsingHua University, Beijing, P.R. China#TAB#"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, P.R. China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"TsingHua University, Beijing, P.R. China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103733614","display_name":"Wei\u2010Ying Ma","orcid":"https://orcid.org/0000-0002-7384-0735"},"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"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Wei-Ying Ma","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P.R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101683584"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.3106,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.89327832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"334","last_page":"341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"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/T10028","display_name":"Topic Modeling","score":0.9940999746322632,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7432604432106018},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6215155720710754},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.605040431022644},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5475841164588928},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5238364338874817},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4653260409832001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44523343443870544},{"id":"https://openalex.org/keywords/polysemy","display_name":"Polysemy","score":0.4396764039993286},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.41486552357673645},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37578877806663513}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7432604432106018},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6215155720710754},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.605040431022644},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5475841164588928},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5238364338874817},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4653260409832001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44523343443870544},{"id":"https://openalex.org/C2780276568","wikidata":"https://www.wikidata.org/wiki/Q191928","display_name":"Polysemy","level":2,"score":0.4396764039993286},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.41486552357673645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37578877806663513},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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":4,"locations":[{"id":"doi:10.1145/1031171.1031240","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031171.1031240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the thirteenth ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.298.6055","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.298.6055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ust.hk/~qyang/Docs/2004/p334-liu.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.96.2812","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.96.2812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aidb.cs.iitm.ernet.in/cs625/ReadingAssignment/LearningSim-No-OrthogonalSpaces-CIKM2004-p286.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-21334","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-21334","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W195378107","https://openalex.org/W637241713","https://openalex.org/W1493036841","https://openalex.org/W1564518192","https://openalex.org/W1660390307","https://openalex.org/W1956559956","https://openalex.org/W1964348731","https://openalex.org/W1965452491","https://openalex.org/W2035411645","https://openalex.org/W2079922908","https://openalex.org/W2098028660","https://openalex.org/W2117154949","https://openalex.org/W2118393783","https://openalex.org/W2142845314","https://openalex.org/W2147152072","https://openalex.org/W2161453060","https://openalex.org/W2170654002","https://openalex.org/W2914932700","https://openalex.org/W4285719527","https://openalex.org/W6681124392"],"related_works":["https://openalex.org/W2389818373","https://openalex.org/W2220831889","https://openalex.org/W4312683641","https://openalex.org/W3027421045","https://openalex.org/W2576320324","https://openalex.org/W2980386803","https://openalex.org/W3215994059","https://openalex.org/W2319823519","https://openalex.org/W4206798987","https://openalex.org/W2801158176"],"abstract_inverted_index":{"Many":[0],"machine":[1],"learning":[2],"and":[3,44,72,106,117,132],"data":[4,92,107],"mining":[5],"algorithms":[6,75],"crucially":[7],"rely":[8],"on":[9],"the":[10,18,29,47,53,56,90,102],"similarity":[11,33,49,134],"metrics.":[12],"The":[13],"Cosine":[14,48],"similarity,":[15],"which":[16,63],"calculates":[17],"inner":[19],"product":[20],"of":[21,28],"two":[22],"normalized":[23],"feature":[24],"vectors,":[25],"is":[26,50,59],"one":[27],"most":[30],"commonly":[31],"used":[32,83],"measures.":[34],"However,":[35],"in":[36,114],"many":[37],"practical":[38],"tasks":[39],"such":[40,76],"as":[41,77],"text":[42],"categorization":[43],"document":[45],"clustering,":[46],"calculated":[51],"under":[52],"assumption":[54],"that":[55],"input":[57],"space":[58,62],"an":[60,94],"orthogonal":[61,95],"usually":[64],"could":[65],"not":[66],"be":[67],"satisfied":[68],"due":[69],"to":[70,84,112],"synonymy":[71],"polysemy.":[73],"Various":[74],"Latent":[78],"Semantic":[79],"Indexing":[80],"(LSI)":[81],"were":[82],"solve":[85],"this":[86,126],"problem":[87],"by":[88],"projecting":[89],"original":[91],"into":[93],"space.":[96],"However":[97],"LSI":[98],"also":[99],"suffered":[100],"from":[101],"high":[103],"computational":[104],"cost":[105],"sparseness.":[108],"These":[109],"shortcomings":[110],"led":[111],"increases":[113],"computation":[115],"time":[116],"storage":[118],"requirements":[119],"for":[120],"large":[121],"scale":[122],"realistic":[123],"data.":[124],"In":[125],"paper,":[127],"we":[128],"propose":[129],"a":[130],"novel":[131],"effective":[133]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}