{"id":"https://openalex.org/W2061382457","doi":"https://doi.org/10.1145/1964897.1964900","title":"Latent semantic indexing (LSI) fails for TREC collections","display_name":"Latent semantic indexing (LSI) fails for TREC collections","publication_year":2011,"publication_date":"2011-03-31","ids":{"openalex":"https://openalex.org/W2061382457","doi":"https://doi.org/10.1145/1964897.1964900","mag":"2061382457"},"language":"en","primary_location":{"id":"doi:10.1145/1964897.1964900","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1964897.1964900","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-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/A5078548229","display_name":"Avinash Atreya","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avinash Atreya","raw_affiliation_strings":["University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038246567","display_name":"Charles Elkan","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Elkan","raw_affiliation_strings":["University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":4.3138,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.94327342,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"12","issue":"2","first_page":"5","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9959999918937683,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9950000047683716,"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":0.8775017261505127},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6680546998977661},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.6447268128395081},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6422911286354065},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6081989407539368},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5387678146362305},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5136746764183044},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.450168639421463},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4104927182197571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37814396619796753},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3590388298034668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8775017261505127},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6680546998977661},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.6447268128395081},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6422911286354065},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6081989407539368},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5387678146362305},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5136746764183044},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.450168639421463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4104927182197571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37814396619796753},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3590388298034668},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1964897.1964900","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1964897.1964900","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.188.4268","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.188.4268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.kdd.org/explorations/issues/12-2-2010-12/v12-02-3-UR-Elkan.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W32791291","https://openalex.org/W1534523911","https://openalex.org/W2006996936","https://openalex.org/W2014415866","https://openalex.org/W2051172423","https://openalex.org/W2057870902","https://openalex.org/W2073722401","https://openalex.org/W2076227143","https://openalex.org/W2110480283","https://openalex.org/W2114198958","https://openalex.org/W2147152072","https://openalex.org/W2158201212","https://openalex.org/W2169901824","https://openalex.org/W2170907675","https://openalex.org/W2560674852","https://openalex.org/W2613433911","https://openalex.org/W4233760227"],"related_works":["https://openalex.org/W2420905679","https://openalex.org/W2147688565","https://openalex.org/W2782904003","https://openalex.org/W2066043610","https://openalex.org/W2118633810","https://openalex.org/W2150953077","https://openalex.org/W4226434912","https://openalex.org/W2002598339","https://openalex.org/W2133814741","https://openalex.org/W1995410415"],"abstract_inverted_index":{"The":[0,137],"aim":[1],"of":[2,90,102,144,154],"latent":[3],"semantic":[4],"indexing":[5],"(LSI)":[6],"is":[7,63],"to":[8,36,116],"uncover":[9],"the":[10,20,49,60,88,100,109,118,131,141],"relationships":[11],"between":[12],"terms,":[13],"hidden":[14],"concepts,":[15],"and":[16,54,105],"documents.":[17],"LSI":[18,35,43,69,110,122,145,149,156],"uses":[19],"matrix":[21],"factorization":[22],"technique":[23],"known":[24],"as":[25],"singular":[26],"value":[27],"decomposition":[28],"(SVD).":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,66,76,93,113],"apply":[34],"standard":[37],"benchmark":[38],"collections.":[39,56],"We":[40,57],"find":[41],"that":[42,59,78,98,140],"yields":[44],"poor":[45],"retrieval":[46,162],"accuracy":[47,163],"on":[48,130],"TREC":[50,133],"2,":[51],"7,":[52],"8,":[53],"2004":[55],"believe":[58],"negative":[61],"result":[62],"robust,":[64],"because":[65],"try":[67],"more":[68],"variants":[70,143],"than":[71],"any":[72],"previous":[73,148],"work.":[74],"First,":[75],"show":[77,114,139],"using":[79,155],"Okapi":[80],"BM25":[81,119],"weights":[82],"for":[83],"terms":[84],"in":[85,108,161],"documents":[86],"improves":[87],"performance":[89],"LSI.":[91],"Second,":[92],"derive":[94],"novel":[95],"scoring":[96],"methods":[97,126],"implement":[99],"ideas":[101],"query":[103],"expansion":[104],"score":[106],"regularization":[107],"framework.":[111],"Third,":[112],"how":[115],"combine":[117],"method":[120],"with":[121],"methods.":[123,150],"All":[124],"proposed":[125],"are":[127],"evaluated":[128],"experimentally":[129],"four":[132],"collections":[134],"mentioned":[135],"above.":[136],"experiments":[138],"new":[142],"improve":[146],"upon":[147],"Nevertheless,":[151],"no":[152],"way":[153],"achieves":[157],"a":[158],"worthwhile":[159],"improvement":[160],"over":[164],"BM25.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}