{"id":"https://openalex.org/W1278110899","doi":"https://doi.org/10.7916/d80z72c3","title":"Dimension Reduction for Short Text Similarity and its Applications","display_name":"Dimension Reduction for Short Text Similarity and its Applications","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1278110899","doi":"https://doi.org/10.7916/d80z72c3","mag":"1278110899"},"language":"en","primary_location":{"id":"pmh:oai:academiccommons.columbia.edu:10.7916/D80Z72C3","is_oa":false,"landing_page_url":"https://doi.org/10.7916/D80Z72C3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Theses"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7916/d80z72c3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027639981","display_name":"Weiwei Guo","orcid":"https://orcid.org/0000-0001-5037-0972"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guo, Weiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5027639981"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.5416482090950012},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5274781584739685},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5145558714866638},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4810226559638977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4381406605243683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4206226170063019},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3888779580593109},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34748244285583496},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.26900047063827515},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.10809585452079773}],"concepts":[{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.5416482090950012},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5274781584739685},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5145558714866638},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4810226559638977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4381406605243683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4206226170063019},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3888779580593109},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34748244285583496},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.26900047063827515},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.10809585452079773},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:academiccommons.columbia.edu:10.7916/D80Z72C3","is_oa":false,"landing_page_url":"https://doi.org/10.7916/D80Z72C3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Theses"},{"id":"mag:1278110899","is_oa":false,"landing_page_url":"https://academiccommons.columbia.edu/doi/10.7916/D80Z72C3","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null},{"id":"doi:10.7916/d80z72c3","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d80z72c3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.7916/d80z72c3","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d80z72c3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":111,"referenced_works":["https://openalex.org/W19743771","https://openalex.org/W37473190","https://openalex.org/W53063441","https://openalex.org/W91442942","https://openalex.org/W92973652","https://openalex.org/W135437175","https://openalex.org/W145425800","https://openalex.org/W154847150","https://openalex.org/W155754185","https://openalex.org/W563334283","https://openalex.org/W1489476898","https://openalex.org/W1490768968","https://openalex.org/W1503071992","https://openalex.org/W1521365985","https://openalex.org/W1566018662","https://openalex.org/W1590495275","https://openalex.org/W1654370055","https://openalex.org/W1731244441","https://openalex.org/W1859173823","https://openalex.org/W1880262756","https://openalex.org/W1959533457","https://openalex.org/W1969486090","https://openalex.org/W1971220772","https://openalex.org/W1974712809","https://openalex.org/W1980776243","https://openalex.org/W1990514682","https://openalex.org/W1990537115","https://openalex.org/W1991862576","https://openalex.org/W1992665562","https://openalex.org/W1996430422","https://openalex.org/W1997452128","https://openalex.org/W2012833704","https://openalex.org/W2020360881","https://openalex.org/W2023111600","https://openalex.org/W2031026221","https://openalex.org/W2036859039","https://openalex.org/W2038721957","https://openalex.org/W2063202923","https://openalex.org/W2065157922","https://openalex.org/W2072644219","https://openalex.org/W2081193615","https://openalex.org/W2084363474","https://openalex.org/W2088911157","https://openalex.org/W2091812280","https://openalex.org/W2096423148","https://openalex.org/W2096550403","https://openalex.org/W2097606805","https://openalex.org/W2101105183","https://openalex.org/W2101251342","https://openalex.org/W2101761627","https://openalex.org/W2103305545","https://openalex.org/W2107743791","https://openalex.org/W2109450467","https://openalex.org/W2112688502","https://openalex.org/W2112740777","https://openalex.org/W2113522550","https://openalex.org/W2114524997","https://openalex.org/W2115792525","https://openalex.org/W2116555906","https://openalex.org/W2119759918","https://openalex.org/W2119775030","https://openalex.org/W2121147707","https://openalex.org/W2121184547","https://openalex.org/W2123661878","https://openalex.org/W2124251782","https://openalex.org/W2124732071","https://openalex.org/W2127128140","https://openalex.org/W2128809169","https://openalex.org/W2129468719","https://openalex.org/W2132019450","https://openalex.org/W2135875128","https://openalex.org/W2137607259","https://openalex.org/W2137958601","https://openalex.org/W2147152072","https://openalex.org/W2147192413","https://openalex.org/W2150159277","https://openalex.org/W2150824314","https://openalex.org/W2151170651","https://openalex.org/W2152180407","https://openalex.org/W2152336115","https://openalex.org/W2152815769","https://openalex.org/W2153702313","https://openalex.org/W2154524383","https://openalex.org/W2154652894","https://openalex.org/W2157835502","https://openalex.org/W2164290393","https://openalex.org/W2165395308","https://openalex.org/W2168185617","https://openalex.org/W2169279899","https://openalex.org/W2180724871","https://openalex.org/W2209961975","https://openalex.org/W2221852422","https://openalex.org/W2250387780","https://openalex.org/W2250489604","https://openalex.org/W2250565861","https://openalex.org/W2250925602","https://openalex.org/W2251291469","https://openalex.org/W2251607282","https://openalex.org/W2251717670","https://openalex.org/W2251864938","https://openalex.org/W2293597654","https://openalex.org/W2436001372","https://openalex.org/W2525127255","https://openalex.org/W2613678836","https://openalex.org/W2950225692","https://openalex.org/W2951255215","https://openalex.org/W2951798058","https://openalex.org/W2952186591","https://openalex.org/W2952672548","https://openalex.org/W2953332543","https://openalex.org/W3088413834"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"due":[1],"to":[2,24,47,158,197,274,333,341,394,447,472,489,537,554,593,619,622,746,769,777,786],"the":[3,11,44,54,67,71,80,84,90,115,152,160,191,199,207,217,221,228,235,239,245,256,261,263,317,339,343,348,358,381,406,421,440,467,481,486,520,533,544,571,595,608,670,685,690,714,778,783,788,799,815,824],"burst":[4],"of":[5,10,13,56,69,83,106,177,224,323,347,570,692,765,782,790,823],"online":[6],"text":[7,76,85,100,109,116,143,226,328,340,408,506,522,546],"data,":[8,86],"much":[9,475,532],"focus":[12],"natural":[14],"language":[15],"processing":[16],"(NLP)":[17],"research":[18],"has":[19,131],"shifted":[20],"from":[21,38,308,375],"long":[22],"documents":[23],"shorter":[25],"ones":[26],"such":[27],"as":[28,227,474,478,737,739],"sentences":[29],"and":[30,87,151,289,370,392,431,509,680,695,718,757,802,812],"utterances.":[31],"However,":[32],"short":[33,75,99,108,208,327,359,407,505,521,545],"texts":[34,178],"posit":[35],"significant":[36,821],"challenges":[37],"an":[39],"NLP":[40,95,539,550],"perspective":[41],"especially":[42],"if":[43],"goal":[45],"is":[46,111,213,331,352,568,676,774,785],"get":[48],"at":[49,753],"sentence":[50,120,130],"level":[51],"semantics":[52,161,379],"in":[53,93,114,141,206,216,231,238,255,321,338,411,428,480,503,519,579,607,629,814,829],"absence":[55],"larger":[57],"contexts.":[58],"Motivated":[59],"by":[60,78,249,710,793],"this":[61,63,164,362,620,749],"challenge,":[62],"thesis":[64],"focuses":[65],"on":[66,127,435,611,656,689,713],"problem":[68,410],"predicting":[70],"similarity":[72,101,110,121,409,461,507,523,547,559,659,664,674,686,707],"between":[73,466,697],"two":[74,667,698],"samples":[77],"extracting":[79],"latent":[81,175,290],"representation":[82,156,176],"we":[88,166,195,364,443,484,542,751],"apply":[89,616],"resulting":[91,498,632],"models":[92,172],"various":[94,830],"tasks":[96,551],"that":[97,203,212,248,661,773],"involves":[98],"computation.":[102],"The":[103,241,384,497,565,631,647,724,780],"major":[104],"challenge":[105],"computing":[107],"insufficient":[112],"information":[113,356,389],"snippets.":[117],"In":[118,260,470,748],"a":[119,129,142,210,225,232,252,376,417,429,453,510,657,663,704,762,767,770,791,794],"benchmark":[122],"[Agirre":[123],"et":[124,280,295,599],"al.,":[125,281,296],"2012],":[126],"average":[128],"10.8":[132],"words.":[133,310],"Hence,":[134],"there":[135,351],"are":[136,148,204,390,517,528],"very":[137,353,637],"few":[138,354],"overlapping":[139,693],"words":[140,201,223,237,247,301,307,373,694],"pair":[144],"even":[145],"when":[146],"they":[147],"semantically":[149],"related,":[150],"widely":[153],"used":[154],"bag-of-words":[155],"fails":[157],"captures":[159],"relatedness.":[162],"To":[163,189,361,438],"end,":[165,363],"propose":[167,196,703,761],"several":[168,549],"weighted":[169,267],"matrix":[170,257,268],"factorization":[171,258],"for":[173,400,548,575,603],"learning":[174],",":[179],"which":[180,283,298,556,581,683],"induces":[181],"meaningful":[182],"similar":[183],"scores:":[184],"1.":[185],"Modeling":[186,312],"Missing":[187],"Words:":[188],"address":[190],"word":[192,337,613],"sparsity":[193],"issue,":[194],"model":[198,242,265,320,335,499,534,618,801,826],"missing":[200,222,246,287,300,306],"(words":[202],"not":[205,285,304,515],"text),":[209],"feature":[211],"typically":[214],"overlooked":[215],"literature.":[218],"We":[219,315,404,514,615,702,760,797],"define":[220],"whole":[229],"vocabulary":[230],"corpus":[233,367],"minus":[234],"observed":[236,309],"text.":[240],"carefully":[243],"handles":[244],"assigning":[250],"them":[251,433],"small":[253],"weight":[254],"framework.":[259],"experiments,":[262],"new":[264,705,763,816,825],"{\\it":[266],"factorization}":[269],"(WMF)":[270,319],"achieves":[271],"superior":[272],"performance":[273,502],"Latent":[275],"Dirichlet":[276],"Allocation":[277],"(LDA)":[278],"[Blei":[279],"2003],":[282,682],"does":[284,303],"use":[286],"words,":[288],"semantic":[291,345],"analysis":[292],"(LSA)":[293],"[Deerwester":[294],"1990],":[297],"uses":[299],"but":[302,526],"distinguish":[305],"2.":[311],"Lexical":[313],"Semantics:":[314],"improve":[316],"previous":[318],"terms":[322],"lexical":[324,378],"semantics.":[325],"For":[326],"similarity,":[329],"it":[330],"crucial":[332],"robustly":[334],"each":[336,395,449],"capture":[342],"complete":[344],"picture":[346],"text,":[349],"since":[350],"repetitive":[355],"given":[357,416,666],"context.":[360],"incorporate":[365,803],"both":[366,387,504],"based":[368,434,610,688,734,741],"(bigrams)":[369],"knowledge-based":[371],"(similar":[372],"extracted":[374],"dictionary)":[377],"into":[380,452],"WMF":[382,617,712,800],"model.":[383,817],"experiments":[385,819],"show":[386,820],"additional":[388],"helpful":[391],"complementary":[393],"other.":[396],"3.":[397],"Similarity":[398],"Computing":[399],"Large-scale":[401],"data":[402,426,450,477,717,756],"sets:":[403],"tackle":[405],"large":[412],"scale":[413],"setting,":[414],"i.e.,":[415,808],"query":[418],"tweet,":[419],"compute":[420],"similarity/distance":[422,436],"with":[423,530,639],"all":[424],"other":[425,538],"point":[427],"database,":[430],"rank":[432],"score.":[437],"reduce":[439,494],"computation":[441],"time,":[442],"exploit":[444],"binary":[445,455,482],"coding":[446],"transform":[448],"sample":[451],"compact":[454],"code,":[456],"hence":[457,493],"enables":[458],"highly":[459,654],"efficient":[460],"computations":[462],"via":[463],"Hamming":[464],"distances":[465],"generated":[468],"codes.":[469],"order":[471],"preserve":[473],"original":[476],"possible":[479],"bits,":[483],"restrict":[485],"projection":[487],"directions":[488],"be":[490],"nearly":[491],"orthogonal":[492],"redundant":[495],"information.":[496],"demonstrate":[500],"better":[501],"task":[508,524,621,750,764,784],"tweet":[511,768,792],"retrieval":[512],"task.":[513],"only":[516],"interested":[518],"itself,":[525],"also":[527],"concerned":[529],"how":[531],"could":[535],"contribute":[536],"tasks.":[540],"Accordingly,":[541],"adapt":[543],"closely":[552],"associated":[553],"semantics,":[555],"involve":[557],"intensive":[558],"computation:":[560],"4.":[561],"Text":[562],"Summarization":[563],"Evaluation:":[564],"pyramid":[566,634,641],"method":[567],"one":[569],"most":[572,671,775],"popular":[573,672],"methods":[574],"evaluating":[576],"content":[577],"selection":[578],"summarization,":[580],"requires":[582],"manual":[583,640],"inspection":[584],"during":[585],"evaluation.":[586],"Recently":[587],"some":[588],"efforts":[589],"have":[590],"been":[591],"made":[592],"automate":[594],"evaluation":[596,831],"process:":[597],"Harnly":[598],"al.":[600],"(2005)":[601],"searched":[602],"key":[604,626],"facts/concepts":[605],"covered":[606],"summaries":[609],"surface":[612,732],"matching.":[614],"enable":[623],"more":[624],"accurate":[625],"facts":[627],"identification":[628],"summaries.":[630],"automated":[633],"scores":[635],"correlate":[636],"well":[638,738],"scores.":[642],"5.":[643],"Word":[644,649],"Sense":[645,650],"Disambiguation:":[646],"unsupervised":[648],"Disambiguation":[651],"(WSD)":[652],"systems":[653],"rely":[655],"sense":[658,673,706,715],"module":[660],"returns":[662],"score":[665,687],"senses.":[668],"Currently":[669],"measure":[675,708],"Extended":[677],"Lesk":[678],"[Banerjee":[679],"Pedersen,":[681],"calculates":[684],"number":[691],"phrases":[696],"extended":[699],"dictionary":[700],"definitions.":[701],"wmfvec":[709,728],"running":[711],"definition":[716],"integrating":[719],"WordNet":[720],"[Fellbaum,":[721],"1998]":[722],"features.":[723],"WSD":[725,735],"system":[726],"using":[727],"significantly":[729],"outperforms":[730],"traditional":[731],"form":[733],"algorithms":[736],"LDA":[740],"systems.":[742],"6.":[743],"Linking":[744],"Tweets":[745],"News:":[747],"target":[752],"social":[754],"media":[755],"news":[758,771,795],"data.":[759],"linking":[766],"article":[772],"relevant":[776],"tweet.":[779],"motivation":[781],"argument":[787],"context":[789],"article.":[796],"extend":[798],"multiple":[804],"Twitter/news":[805],"specific":[806],"features,":[807],"hashtag,":[809],"named":[810],"entities":[811],"timestamps,":[813],"Our":[818],"improvement":[822],"over":[827],"baselines":[828],"metrics.":[832]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}