{"id":"https://openalex.org/W2107535552","doi":"https://doi.org/10.1145/1183614.1183710","title":"Text classification improved through multigram models","display_name":"Text classification improved through multigram models","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2107535552","doi":"https://doi.org/10.1145/1183614.1183710","mag":"2107535552"},"language":"en","primary_location":{"id":"doi:10.1145/1183614.1183710","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183614.1183710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM international conference on Information and knowledge management  - CIKM '06","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/A5105366551","display_name":"Dou Shen","orcid":null},"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":true,"raw_author_name":"Dou Shen","raw_affiliation_strings":["Hong Kong University of Science and Technology","Hong Kong University of Science & Technology"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University of Science & Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102139311","display_name":"Jian-Tao Sun","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":"Jian-Tao Sun","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/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 University of Science & Technology"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University of Science & Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5105366551"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":1.8629,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.87643864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"672","last_page":"672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","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/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7219159007072449},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.6963165998458862},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.588315486907959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5620957612991333},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5459631085395813},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5227506160736084},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.4928872585296631},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4417555630207062},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.42862269282341003},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4285297393798828},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.41844114661216736},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3950516879558563},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3707311749458313},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1494746208190918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7219159007072449},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.6963165998458862},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.588315486907959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5620957612991333},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5459631085395813},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5227506160736084},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.4928872585296631},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4417555630207062},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.42862269282341003},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4285297393798828},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.41844114661216736},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3950516879558563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3707311749458313},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1494746208190918},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1183614.1183710","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183614.1183710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM international conference on Information and knowledge management  - CIKM '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.298.7585","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.298.7585","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/2006/p672-shen.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-37546","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-37546","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":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W140312209","https://openalex.org/W1510372738","https://openalex.org/W1574901103","https://openalex.org/W1600320866","https://openalex.org/W1607753411","https://openalex.org/W1833785989","https://openalex.org/W1846766366","https://openalex.org/W1854214752","https://openalex.org/W1963742467","https://openalex.org/W2021294551","https://openalex.org/W2049633694","https://openalex.org/W2053463056","https://openalex.org/W2102381086","https://openalex.org/W2113641473","https://openalex.org/W2114535528","https://openalex.org/W2134237567","https://openalex.org/W2135399286","https://openalex.org/W2141734078","https://openalex.org/W2149684865","https://openalex.org/W2150102617","https://openalex.org/W2151752770","https://openalex.org/W2158195707","https://openalex.org/W2160053217","https://openalex.org/W2404470863","https://openalex.org/W2435251607","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W13363956","https://openalex.org/W1530472511","https://openalex.org/W1505979446","https://openalex.org/W3107474891","https://openalex.org/W2177862353","https://openalex.org/W3033932319","https://openalex.org/W2351428524","https://openalex.org/W4366968113","https://openalex.org/W2108632689","https://openalex.org/W2956042246"],"abstract_inverted_index":{"Classification":[0],"algorithms":[1],"and":[2,88,155,161,168],"document":[3,13,60,182],"representation":[4,61,183],"approaches":[5],"are":[6],"two":[7,95],"key":[8],"elements":[9],"for":[10],"a":[11,58],"successful":[12],"classification":[14,97,120],"system.":[15],"In":[16,53],"the":[17,34,47,73,78,115,124,131,143,150,159,177],"past,":[18],"much":[19,138],"work":[20],"has":[21],"been":[22],"conducted":[23],"to":[24,28,166,170],"find":[25],"better":[26,119],"ways":[27],"represent":[29],"documents.":[30],"However,":[31],"most":[32],"of":[33,49,134,142,152,179],"attempts":[35],"rely":[36],"on":[37,64,84,101,109,127,149],"certain":[38],"extra":[39],"resources":[40],"such":[41],"as":[42],"WordNet,":[43],"or":[44,117],"they":[45],"face":[46],"problem":[48],"extremely":[50],"high":[51],"dimension.":[52],"this":[54],"paper,":[55],"we":[56,92],"propose":[57],"new":[59],"approach":[62,69],"based":[63,108,126,148],"n-multigram":[65,85,110,153],"language":[66,86,90],"models.":[67],"This":[68],"can":[70,113],"automatically":[71],"discover":[72],"hidden":[74],"semantic":[75],"sequences":[76],"in":[77],"documents":[79],"under":[80],"each":[81],"category.":[82],"Based":[83],"models":[87,111,129,154,157],"n-gram":[89,128,156],"models,":[91],"put":[93],"forward":[94],"text":[96],"algorithms.":[98],"The":[99],"experiments":[100],"RCV1":[102],"show":[103],"that":[104,141],"our":[105,135,180],"proposed":[106,146,181],"algorithm":[107,136,147],"alone":[112],"achieve":[114],"similar":[116],"even":[118],"performance":[121],"compared":[122],"with":[123],"classifier":[125],"but":[130],"model":[132],"size":[133],"is":[137],"smaller":[139],"than":[140],"latter.":[144],"Another":[145],"combination":[151],"improves":[158],"micro-F1":[160],"macro-F1":[162],"values":[163],"from":[164],"89.5%":[165],"92.6%":[167],"87.2%":[169],"91.1%":[171],"respectively.":[172],"All":[173],"these":[174],"observations":[175],"support":[176],"validity":[178],"approach.":[184]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}