{"id":"https://openalex.org/W63056884","doi":null,"title":"Unsupervised cleansing of noisy text","display_name":"Unsupervised cleansing of noisy text","publication_year":2010,"publication_date":"2010-08-23","ids":{"openalex":"https://openalex.org/W63056884","mag":"63056884"},"language":"en","primary_location":{"id":"mag:63056884","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/C10-2022.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419219","display_name":"International Conference on Computational Linguistics","issn_l":"1525-2477","issn":["1525-2477"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Computational Linguistics","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5082114795","display_name":"Danish Contractor","orcid":"https://orcid.org/0000-0002-6843-1961","observed_orcids":["https://orcid.org/0000-0002-6843-1961"]},"institutions":[{"id":"https://openalex.org/I4210129961","display_name":"IBM (India)","ror":"https://ror.org/034ahpr11","country_code":"IN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210129961"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Danish Contractor","raw_affiliation_strings":["IBM India Software Lab"],"raw_orcid":"https://orcid.org/0000-0002-6843-1961","affiliations":[{"raw_affiliation_string":"IBM India Software Lab","institution_ids":["https://openalex.org/I4210129961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004954473","display_name":"Tanveer Afzal Faruquie","orcid":"https://orcid.org/0009-0008-9474-7928","observed_orcids":["https://orcid.org/0009-0008-9474-7928"]},"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/I4210129961","display_name":"IBM (India)","ror":"https://ror.org/034ahpr11","country_code":"IN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210129961"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanveer A. Faruquie","raw_affiliation_strings":["\u2022 IBM Research \u2014 India#TAB#"],"raw_orcid":"https://orcid.org/0009-0008-9474-7928","affiliations":[{"raw_affiliation_string":"\u2022 IBM Research \u2014 India#TAB#","institution_ids":["https://openalex.org/I4210103279","https://openalex.org/I4210129961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110629023","display_name":"L. Venkata Subramaniam","orcid":"https://orcid.org/0009-0001-3897-9758","observed_orcids":["https://orcid.org/0009-0001-3897-9758"]},"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/I4210129961","display_name":"IBM (India)","ror":"https://ror.org/034ahpr11","country_code":"IN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210129961"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"L. Venkata Subramaniam","raw_affiliation_strings":["\u2022 IBM Research \u2014 India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2022 IBM Research \u2014 India#TAB#","institution_ids":["https://openalex.org/I4210103279","https://openalex.org/I4210129961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.6812,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.98389897,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"189","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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":0.0010999999940395355,"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/T13155","display_name":"Digital Communication and Language","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.7120000123977661},{"id":"https://openalex.org/keywords/statistical-machine-translation","display_name":"statistical machine translation","score":0.9869999885559082},{"id":"https://openalex.org/keywords/informal-communication","display_name":"informal communication","score":0.6539999842643738},{"id":"https://openalex.org/keywords/sms","display_name":"SMS","score":0.7680000066757202},{"id":"https://openalex.org/keywords/twitter","display_name":"Twitter","score":0.8799999952316284},{"id":"https://openalex.org/keywords/chat","display_name":"chat","score":0.609000027179718},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.33500000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8398690223693848},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7678307890892029},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7656007409095764},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6288744807243347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.605984628200531},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5954684019088745},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5653978586196899},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.4556494355201721},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3809233605861664},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:63056884","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/C10-2022.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419219","display_name":"International Conference on Computational Linguistics","issn_l":"1525-2477","issn":["1525-2477"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Computational Linguistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W24068845","https://openalex.org/W1497763703","https://openalex.org/W1555286493","https://openalex.org/W1560797130","https://openalex.org/W1972648128","https://openalex.org/W2006969979","https://openalex.org/W2035227369","https://openalex.org/W2038647974","https://openalex.org/W2049840989","https://openalex.org/W2053966956","https://openalex.org/W2101200183","https://openalex.org/W2109088983","https://openalex.org/W2114066462","https://openalex.org/W2124807415","https://openalex.org/W2158164089","https://openalex.org/W2163942301","https://openalex.org/W2586887417"],"related_works":["https://openalex.org/W7100891350","https://openalex.org/W2033523543","https://openalex.org/W2007433094","https://openalex.org/W3115229845","https://openalex.org/W2971254483","https://openalex.org/W2988335601","https://openalex.org/W7095307775","https://openalex.org/W6990188342","https://openalex.org/W3168709314","https://openalex.org/W3008216235"],"abstract_inverted_index":{"In":[0,50],"this":[1,51],"paper":[2,52],"we":[3,53],"look":[4],"at":[5],"the":[6,59,98,101,105],"problem":[7],"of":[8,61,80,100],"cleansing":[9],"noisy":[10,46,62,75,86],"text":[11,19,44,63],"using":[12],"a":[13,73,77],"statistical":[14],"machine":[15],"translation":[16,60],"model.":[17],"Noisy":[18],"is":[20,40,93],"produced":[21],"in":[22],"informal":[23],"communications":[24],"such":[25],"as":[26],"Short":[27],"Message":[28],"Service":[29],"(SMS),":[30],"Twitter":[31],"and":[32,47,104],"chat.":[33],"A":[34],"typical":[35],"Statistical":[36],"Machine":[37],"Translation":[38],"system":[39],"trained":[41],"on":[42],"parallel":[43],"comprising":[45],"clean":[48,65,82,91],"sentences.":[49],"propose":[54],"an":[55],"unsupervised":[56],"method":[57,68],"for":[58,84],"to":[64],"text.":[66],"Our":[67],"has":[69],"two":[70],"steps.":[71],"For":[72],"given":[74],"sentence,":[76],"weighted":[78,102],"list":[79],"possible":[81],"tokens":[83],"each":[85],"token":[87],"are":[88],"obtained.":[89],"The":[90],"sentence":[92],"then":[94],"obtained":[95],"by":[96],"maximizing":[97],"product":[99],"lists":[103],"language":[106],"model":[107],"scores.":[108]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":8}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}