{"id":"https://openalex.org/W1552936656","doi":"https://doi.org/10.1109/retis.2015.7232908","title":"Text normalization in code-mixed social media text","display_name":"Text normalization in code-mixed social media text","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1552936656","doi":"https://doi.org/10.1109/retis.2015.7232908","mag":"1552936656"},"language":"en","primary_location":{"id":"doi:10.1109/retis.2015.7232908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/retis.2015.7232908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)","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/A5031548635","display_name":"Sukanya Dutta","orcid":null},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sukanya Dutta","raw_affiliation_strings":["Department of Computer Science & Engineering, Jadavpur University, Kolkata, India","[Department of Computer Science & Engineering, Jadavpur University, Kolkata, India]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Jadavpur University, Kolkata, India","institution_ids":["https://openalex.org/I170979836"]},{"raw_affiliation_string":"[Department of Computer Science & Engineering, Jadavpur University, Kolkata, India]","institution_ids":["https://openalex.org/I170979836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001156952","display_name":"Tista Saha","orcid":null},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tista Saha","raw_affiliation_strings":["Department of Computer Science & Engineering, Jadavpur University, Kolkata, India","[Department of Computer Science & Engineering, Jadavpur University, Kolkata, India]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Jadavpur University, Kolkata, India","institution_ids":["https://openalex.org/I170979836"]},{"raw_affiliation_string":"[Department of Computer Science & Engineering, Jadavpur University, Kolkata, India]","institution_ids":["https://openalex.org/I170979836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074867889","display_name":"Somnath Banerjee","orcid":"https://orcid.org/0000-0002-4947-7649"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Somnath Banerjee","raw_affiliation_strings":["Department of Computer Science & Engineering, Jadavpur University, Kolkata, India","[Department of Computer Science & Engineering, Jadavpur University, Kolkata, India]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Jadavpur University, Kolkata, India","institution_ids":["https://openalex.org/I170979836"]},{"raw_affiliation_string":"[Department of Computer Science & Engineering, Jadavpur University, Kolkata, India]","institution_ids":["https://openalex.org/I170979836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070618344","display_name":"Sudip Kumar Naskar","orcid":"https://orcid.org/0000-0003-1588-4665"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudip Kumar Naskar","raw_affiliation_strings":["Department of Computer Science & Engineering, Jadavpur University, Kolkata, India","[Department of Computer Science & Engineering, Jadavpur University, Kolkata, India]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Jadavpur University, Kolkata, India","institution_ids":["https://openalex.org/I170979836"]},{"raw_affiliation_string":"[Department of Computer Science & Engineering, Jadavpur University, Kolkata, India]","institution_ids":["https://openalex.org/I170979836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031548635"],"corresponding_institution_ids":["https://openalex.org/I170979836"],"apc_list":null,"apc_paid":null,"fwci":4.7458,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.95044972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"23","issue":null,"first_page":"378","last_page":"382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T13629","display_name":"Text Readability and Simplification","score":0.9990000128746033,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9904000163078308,"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":0.8598125576972961},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.8026901483535767},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7644021511077881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7040458917617798},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.6778604388237},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.597281277179718},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5186344981193542},{"id":"https://openalex.org/keywords/spell","display_name":"Spell","score":0.4410071074962616},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4341297745704651},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.43192556500434875},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.4176325798034668},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.37973976135253906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3556536138057709},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22324293851852417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8598125576972961},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.8026901483535767},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7644021511077881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7040458917617798},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.6778604388237},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.597281277179718},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5186344981193542},{"id":"https://openalex.org/C2780957641","wikidata":"https://www.wikidata.org/wiki/Q1999796","display_name":"Spell","level":2,"score":0.4410071074962616},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4341297745704651},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.43192556500434875},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.4176325798034668},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.37973976135253906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3556536138057709},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22324293851852417},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/retis.2015.7232908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/retis.2015.7232908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321071","display_name":"Department of Electronics and Information Technology, Ministry of Communications and Information Technology","ror":"https://ror.org/02z31cn83"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1490831147","https://openalex.org/W1632767318","https://openalex.org/W2097478551","https://openalex.org/W2109932952","https://openalex.org/W2123660869","https://openalex.org/W2130988870","https://openalex.org/W2164107060","https://openalex.org/W2172112754","https://openalex.org/W2251794678","https://openalex.org/W2952192369","https://openalex.org/W6629220332","https://openalex.org/W6674467793"],"related_works":["https://openalex.org/W4255929276","https://openalex.org/W2789394886","https://openalex.org/W4392643387","https://openalex.org/W2184839352","https://openalex.org/W2083657536","https://openalex.org/W2042822003","https://openalex.org/W2103233694","https://openalex.org/W2034944613","https://openalex.org/W2044923869","https://openalex.org/W2097478624"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,24,89,99,108,122,130,137],"problem":[4,11,60],"of":[5,23,48,67,103],"text":[6,38],"normalization,":[7],"an":[8],"often":[9],"overlooked":[10],"in":[12,16,34,53,71],"natural":[13],"language":[14,69,91,124],"processing,":[15],"code-mixed":[17,35,72],"social":[18,36,73],"media":[19,37,74],"text.":[20,75],"The":[21,57],"objective":[22],"work":[25],"presented":[26,112],"here":[27,113],"is":[28],"to":[29],"correct":[30],"English":[31,41,139],"spelling":[32,95,104],"errors":[33],"that":[39,66],"contains":[40],"words":[42,49,117],"as":[43,45],"well":[44],"Romanized":[46],"transliteration":[47],"from":[50],"another":[51,64],"language,":[52],"this":[54],"case":[55],"Bangla.":[56],"targeted":[58],"research":[59],"also":[61],"entails":[62],"solving":[63],"problem,":[65],"word-level":[68,90,123],"identification":[70,92,125],"We":[76],"employ":[77],"a":[78],"CRF":[79],"based":[80],"machine":[81],"learning":[82],"approach":[83],"followed":[84],"by":[85],"post-processing":[86],"heuristics":[87],"for":[88],"task.":[93],"For":[94],"correction,":[96],"we":[97],"used":[98],"noisy":[100],"channel":[101],"model":[102,111],"correction.":[105],"In":[106],"addition,":[107],"spell":[109,131],"checker":[110,132],"tackles":[114],"wordplay,":[115],"contracted":[116],"and":[118,129],"phonetic":[119],"variations.":[120],"Overall,":[121],"achieved":[126,133],"90.5%":[127],"accuracy":[128,135],"69.43%":[134],"on":[136],"detected":[138],"words.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
