{"id":"https://openalex.org/W2059993991","doi":"https://doi.org/10.1145/2396761.2398536","title":"From sBoW to dCoT marginalized encoders for text representation","display_name":"From sBoW to dCoT marginalized encoders for text representation","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W2059993991","doi":"https://doi.org/10.1145/2396761.2398536","mag":"2059993991"},"language":"en","primary_location":{"id":"doi:10.1145/2396761.2398536","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","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/A5100820808","display_name":"Zhixiang Xu","orcid":"https://orcid.org/0000-0003-4713-5124"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhixiang (Eddie) Xu","raw_affiliation_strings":["Washington University in St. Louis, St. Louis, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699702","display_name":"Minmin Chen","orcid":"https://orcid.org/0000-0002-7342-9022"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minmin Chen","raw_affiliation_strings":["Washington University in St. Louis, St. Louis, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006380227","display_name":"Kilian Q. Weinberger","orcid":null},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kilian Q. Weinberger","raw_affiliation_strings":["Washington University in St. Louis, St. Louis, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101544732","display_name":"Fei Sha","orcid":"https://orcid.org/0000-0002-9382-0010"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Sha","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA","[University of Southern California Los, Angeles, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[University of Southern California Los, Angeles, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]}],"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":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1879","last_page":"1884"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7752924561500549},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7640237808227539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6848323941230774},{"id":"https://openalex.org/keywords/polysemy","display_name":"Polysemy","score":0.6699572205543518},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5682829022407532},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5237421989440918},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5196503400802612},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5184499621391296},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5179508924484253},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5056350231170654},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5039636492729187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48624861240386963},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.41533344984054565},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3386687636375427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13574838638305664},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1136595606803894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752924561500549},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7640237808227539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6848323941230774},{"id":"https://openalex.org/C2780276568","wikidata":"https://www.wikidata.org/wiki/Q191928","display_name":"Polysemy","level":2,"score":0.6699572205543518},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5682829022407532},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5237421989440918},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5196503400802612},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5184499621391296},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5179508924484253},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5056350231170654},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5039636492729187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48624861240386963},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.41533344984054565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3386687636375427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13574838638305664},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1136595606803894},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2396761.2398536","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.4807","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.4807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.wustl.edu/~mchen/papers/dCoT.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.422.1300","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.422.1300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.wustl.edu/~mchen/papers/msda_dm.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1506806321","https://openalex.org/W1599838312","https://openalex.org/W1625255723","https://openalex.org/W1663973292","https://openalex.org/W1880262756","https://openalex.org/W1978394996","https://openalex.org/W1985697096","https://openalex.org/W2000569744","https://openalex.org/W2017588182","https://openalex.org/W2025768430","https://openalex.org/W2070996757","https://openalex.org/W2078841894","https://openalex.org/W2096873754","https://openalex.org/W2097089247","https://openalex.org/W2102409316","https://openalex.org/W2107743791","https://openalex.org/W2112104211","https://openalex.org/W2113765418","https://openalex.org/W2129921015","https://openalex.org/W2144211451","https://openalex.org/W2146753383","https://openalex.org/W2147152072","https://openalex.org/W2160576670","https://openalex.org/W2165612380","https://openalex.org/W2494779131","https://openalex.org/W2594639291","https://openalex.org/W2949821452","https://openalex.org/W3099514962","https://openalex.org/W4233135949","https://openalex.org/W4234200495","https://openalex.org/W4292023222","https://openalex.org/W6636091599","https://openalex.org/W6636494156"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2376040010","https://openalex.org/W2613880225","https://openalex.org/W2600654830","https://openalex.org/W2053389710"],"abstract_inverted_index":{"In":[0,82],"text":[1,8,57],"mining,":[2],"information":[3],"retrieval,":[4],"and":[5,27,37,43,78,108,131,154],"machine":[6],"learning,":[7],"documents":[9,58],"are":[10,59,67],"commonly":[11],"represented":[12],"through":[13],"variants":[14],"of":[15,18,89,112],"sparse":[16,136],"Bag":[17],"Words":[19],"(sBoW)":[20],"vectors":[21,138],"(e.g.":[22,51,61],"TF-IDF":[23],"[1]).":[24],"Although":[25],"simple":[26],"intuitive,":[28],"sBoW":[29,98,137],"style":[30],"representations":[31],"suffer":[32],"from":[33,127],"their":[34],"inherent":[35],"over-sparsity":[36],"fail":[38],"to":[39,76,95,123],"capture":[40],"word-level":[41],"synonymy":[42],"polysemy.":[44],"Especially":[45],"when":[46],"labeled":[47],"data":[48],"is":[49],"limited":[50],"in":[52,114,162],"document":[53,99,181],"classification),":[54],"or":[55,63],"the":[56,71,115,133,147,156,176],"short":[60],"emails":[62],"abstracts),":[64],"many":[65],"features":[66,173],"rarely":[68],"observed":[69],"within":[70],"training":[72],"corpus.":[73,117],"This":[74],"leads":[75],"overfitting":[77],"reduced":[79],"generalization":[80],"accuracy.":[81],"this":[83,119],"paper":[84],"we":[85],"propose":[86],"Dense":[87],"Cohort":[88],"Terms":[90],"(dCoT),":[91],"an":[92],"unsupervised":[93],"algorithm":[94],"learn":[96],"improved":[97],"features.":[100],"dCoT":[101,121,172],"explicitly":[102],"models":[103],"absent":[104],"words":[105,113,126,130],"by":[106],"removing":[107],"reconstructing":[109],"random":[110],"sub-sets":[111],"unlabeled":[116],"With":[118],"approach,":[120],"learns":[122],"reconstruct":[124],"frequent":[125],"co-occurring":[128],"infrequent":[129],"maps":[132],"high":[134],"dimensional":[135],"into":[139],"a":[140],"low-dimensional":[141],"dense":[142],"representation.":[143],"We":[144,164],"show":[145],"that":[146,155,171],"feature":[148],"removal":[149],"can":[150,158],"be":[151,159],"marginalized":[152],"out":[153],"reconstruction":[157],"solved":[160],"for":[161],"closed-form.":[163],"demonstrate":[165],"empirically,":[166],"on":[167],"several":[168,180],"benchmark":[169],"datasets,":[170],"significantly":[174],"improve":[175],"classification":[177,182],"accuracy":[178],"across":[179],"tasks.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}