{"id":"https://openalex.org/W2514158504","doi":"https://doi.org/10.18653/v1/p16-2002","title":"Scalable Semi-Supervised Query Classification Using Matrix Sketching","display_name":"Scalable Semi-Supervised Query Classification Using Matrix Sketching","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2514158504","doi":"https://doi.org/10.18653/v1/p16-2002","mag":"2514158504"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p16-2002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-2002","pdf_url":"https://www.aclweb.org/anthology/P16-2002.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P16-2002.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010305620","display_name":"Young\u2010Bum Kim","orcid":"https://orcid.org/0000-0001-9471-6330"},"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":"Young-Bum Kim","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061235567","display_name":"Karl Stratos","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karl Stratos","raw_affiliation_strings":["Columbia University, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072875068","display_name":"Ruhi Sarikaya","orcid":"https://orcid.org/0000-0003-2676-2831"},"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":"Ruhi Sarikaya","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9980000257492065,"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":0.9980000257492065,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.996399998664856,"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/T10057","display_name":"Face and Expression Recognition","score":0.9945999979972839,"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":0.8510754704475403},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.799809455871582},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5888341665267944},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.48140573501586914},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.45709413290023804},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43614330887794495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4290160536766052},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.41065704822540283},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4004393219947815},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37228477001190186},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32192718982696533},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23777088522911072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510754704475403},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.799809455871582},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5888341665267944},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.48140573501586914},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.45709413290023804},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43614330887794495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4290160536766052},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41065704822540283},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4004393219947815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37228477001190186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32192718982696533},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23777088522911072},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p16-2002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-2002","pdf_url":"https://www.aclweb.org/anthology/P16-2002.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p16-2002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-2002","pdf_url":"https://www.aclweb.org/anthology/P16-2002.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2514158504.pdf","grobid_xml":"https://content.openalex.org/works/W2514158504.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W648947103","https://openalex.org/W1577871831","https://openalex.org/W1602492977","https://openalex.org/W1980357388","https://openalex.org/W1998058722","https://openalex.org/W2004672974","https://openalex.org/W2008751576","https://openalex.org/W2029445304","https://openalex.org/W2043511823","https://openalex.org/W2063392856","https://openalex.org/W2070996757","https://openalex.org/W2073414385","https://openalex.org/W2079981574","https://openalex.org/W2088424151","https://openalex.org/W2098693229","https://openalex.org/W2137871902","https://openalex.org/W2146446188","https://openalex.org/W2149309710","https://openalex.org/W2171183582","https://openalex.org/W2250539671","https://openalex.org/W2251249950","https://openalex.org/W2251699420","https://openalex.org/W2251816562","https://openalex.org/W2252070015","https://openalex.org/W2295800284","https://openalex.org/W2403246281","https://openalex.org/W2407905223","https://openalex.org/W2750009733","https://openalex.org/W3215084437","https://openalex.org/W4293772237"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2757182831","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385"],"abstract_inverted_index":{"The":[0],"enormous":[1],"scale":[2],"of":[3,30,49,140],"unlabeled":[4,50,141],"text":[5],"available":[6],"today":[7],"necessitates":[8],"scalable":[9],"schemes":[10],"for":[11,60,123],"representation":[12],"learning":[13],"in":[14,20,26,76],"natural":[15],"language":[16],"processing.":[17],"For":[18],"instance,":[19],"this":[21,90],"paper":[22],"we":[23,41,92,128],"are":[24],"interested":[25],"classifying":[27],"the":[28,74,94,103,110,119,131],"intent":[29,133],"a":[31,113],"user":[32,132],"query.":[33],"While":[34],"our":[35],"labeled":[36],"data":[37,75,111],"is":[38,69],"quite":[39],"limited,":[40],"have":[42],"access":[43],"to":[44,56,71,79,100],"virtually":[45],"an":[46],"unlimited":[47],"amount":[48],"queries,":[51],"which":[52],"could":[53],"be":[54],"used":[55],"induce":[57],"useful":[58],"representations:":[59],"instance":[61],"by":[62,136],"principal":[63],"component":[64],"analysis":[65],"(PCA).":[66],"However,":[67],"it":[68],"prohibitive":[70],"even":[72],"store":[73],"memory":[77,115],"due":[78],"its":[80],"sheer":[81],"size,":[82],"let":[83],"alone":[84],"apply":[85,93],"conventional":[86],"batch":[87],"algorithms.":[88],"In":[89],"work,":[91],"recently":[95],"proposed":[96],"matrix":[97,126],"sketching":[98],"algorithm":[99,108],"entirely":[101],"obviate":[102],"problem":[104],"with":[105],"scalability":[106],"This":[107],"approximates":[109],"within":[112],"specified":[114],"bound":[116],"while":[117],"preserving":[118],"covariance":[120],"structure":[121],"necessary":[122],"PCA.":[124],"Using":[125],"sketching,":[127],"significantly":[129],"improve":[130],"classification":[134],"accuracy":[135],"leveraging":[137],"large":[138],"amounts":[139],"queries.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}