{"id":"https://openalex.org/W2123114891","doi":"https://doi.org/10.1145/1390749.1390761","title":"Unsupervised learning of multilingual short message service (SMS) dialect from noisy examples","display_name":"Unsupervised learning of multilingual short message service (SMS) dialect from noisy examples","publication_year":2008,"publication_date":"2008-07-24","ids":{"openalex":"https://openalex.org/W2123114891","doi":"https://doi.org/10.1145/1390749.1390761","mag":"2123114891"},"language":"en","primary_location":{"id":"doi:10.1145/1390749.1390761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","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/A5108351571","display_name":"Sreangsu Acharyya","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sreangsu Acharyya","raw_affiliation_strings":["University of Texas, Austin","University of Texas @ Austin"],"affiliations":[{"raw_affiliation_string":"University of Texas, Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas @ Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109167303","display_name":"Sumit Negi","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Sumit Negi","raw_affiliation_strings":["IBM Indian Research Lab","IBM Indian Research Lab#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Indian Research Lab","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM Indian Research Lab#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110205806","display_name":"L. V. Subramaniam","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"L. V. Subramaniam","raw_affiliation_strings":["IBM Indian Research Lab","IBM Indian Research Lab#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Indian Research Lab","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM Indian Research Lab#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109095821","display_name":"Shourya Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Shourya Roy","raw_affiliation_strings":["IBM Indian Research Lab","IBM Indian Research Lab#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Indian Research Lab","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM Indian Research Lab#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108351571"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":2.2882,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.89992237,"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":"67","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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":0.8212447166442871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.690677285194397},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6278215050697327},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5495402812957764},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5178666114807129},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43204912543296814},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.42729076743125916},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.42679935693740845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212447166442871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.690677285194397},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6278215050697327},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5495402812957764},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5178666114807129},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43204912543296814},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.42729076743125916},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.42679935693740845},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1390749.1390761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W113396932","https://openalex.org/W1480643256","https://openalex.org/W1516111018","https://openalex.org/W2010595692","https://openalex.org/W2049633694","https://openalex.org/W2057900969","https://openalex.org/W2099111195","https://openalex.org/W2101200183","https://openalex.org/W2121227244","https://openalex.org/W2121947440","https://openalex.org/W2125838338","https://openalex.org/W2144226312","https://openalex.org/W2147496287","https://openalex.org/W2160039544","https://openalex.org/W2164107060","https://openalex.org/W4237840503","https://openalex.org/W4285719527","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W2164162849"],"abstract_inverted_index":{"Noise":[0],"in":[1,29,205,226],"textual":[2],"data":[3,38],"such":[4,144],"as":[5],"those":[6],"introduced":[7],"by":[8,53],"multi-linguality,":[9],"misspellings,":[10],"abbreviations,":[11],"deletions,":[12],"phonetic":[13],"spellings,":[14],"non":[15],"standard":[16],"transliteration,":[17],"etc":[18],"pose":[19],"considerable":[20],"problems":[21],"for":[22,101,212],"text-mining.":[23],"Such":[24],"corruptions":[25],"are":[26,61],"very":[27,62],"common":[28],"instant":[30],"messenger":[31],"(IM)":[32],"and":[33,39,64,85,153,194,225,235,250],"short":[34],"message":[35],"service":[36],"(SMS)":[37],"adversely":[40],"affect":[41],"off":[42],"the":[43,83,99,146,155,207,222,228,236],"shelf":[44],"text":[45],"mining":[46],"methods.":[47,55],"Most":[48],"techniques":[49],"address":[50],"this":[51,202],"problem":[52],"supervised":[54,77],"But":[56],"they":[57],"require":[58],"labels":[59],"that":[60,90,118,145,191,206],"expensive":[63,102,208],"time":[65],"consuming":[66],"to":[67,105,122,141,185],"obtain.":[68],"While":[69],"we":[70,88],"do":[71],"not":[72,154],"champion":[73],"unsupervised":[74,91,114],"methods":[75,92,190],"over":[76,133,151,159],"when":[78],"quality":[79],"of":[80,136,164,201,221,239,244],"results":[81,97],"is":[82,116,138,178,246],"supreme":[84],"singular":[86],"concern,":[87],"demonstrate":[89],"can":[93,214],"provide":[94],"cost":[95,170,233],"effective":[96],"without":[98],"need":[100],"human":[103],"intervention":[104],"generate":[106],"parallely":[107],"labelled":[108],"corpora.":[109],"A":[110,128,161],"generative":[111],"model":[112,192],"based":[113,167,176,189],"technique":[115],"presented":[117],"maps":[119],"non-standard":[120],"words":[121,137],"their":[123],"corresponding":[124],"conventional":[125],"frequent":[126],"form.":[127],"Hidden":[129],"Markov":[130],"Model":[131],"(HMM)":[132],"subsequencized":[134],"representation":[135],"used":[139],"subject":[140],"a":[142,173,218],"parameterization":[143],"training":[147],"phase":[148],"involves":[149],"clustering":[150,177],"vectors":[152],"customary":[156],"dynamic":[157],"programming":[158],"sequences.":[160],"principled":[162],"transformation":[163,181],"maximum":[165],"likelihood":[166],"\"central":[168],"clustering\"":[169],"function":[171,234],"into":[172],"\"pairwise":[174],"similarity\"":[175],"proposed.":[179],"This":[180],"makes":[182],"it":[183],"possible":[184],"apply":[186],"\"subsequence":[187],"kernel\"":[188],"delete":[193],"insert":[195],"edit":[196],"operations":[197],"well.":[198],"The":[199],"novelty":[200],"approach":[203,238],"lies":[204],"(Baum-Welch)":[209],"iterations":[210],"required":[211],"HMM,":[213],"be":[215],"avoided":[216],"through":[217],"careful":[219],"factorization":[220],"HMM":[223],"Loglikelihood":[224],"establishing":[227],"connection":[229],"between":[230],"information":[231],"theoretic":[232],"kernel":[237],"machine":[240],"learning.":[241],"Anecdotal":[242],"evidence":[243],"efficacy":[245],"provided":[247],"on":[248],"public":[249],"proprietary":[251],"data.":[252]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}