{"id":"https://openalex.org/W3015869721","doi":"https://doi.org/10.1145/3378414","title":"Machine Normalization","display_name":"Machine Normalization","publication_year":2020,"publication_date":"2020-04-11","ids":{"openalex":"https://openalex.org/W3015869721","doi":"https://doi.org/10.1145/3378414","mag":"3015869721"},"language":"en","primary_location":{"id":"doi:10.1145/3378414","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3378414","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5005008411","display_name":"Randa Zarnoufi","orcid":"https://orcid.org/0000-0002-3353-6704"},"institutions":[{"id":"https://openalex.org/I126477371","display_name":"Mohammed V University","ror":"https://ror.org/00r8w8f84","country_code":"MA","type":"education","lineage":["https://openalex.org/I126477371"]}],"countries":["MA"],"is_corresponding":true,"raw_author_name":"Randa Zarnoufi","raw_affiliation_strings":["Mohammed V University"],"affiliations":[{"raw_affiliation_string":"Mohammed V University","institution_ids":["https://openalex.org/I126477371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047046450","display_name":"Hamid Jaafar","orcid":null},"institutions":[{"id":"https://openalex.org/I119856527","display_name":"Cadi Ayyad University","ror":"https://ror.org/04xf6nm78","country_code":"MA","type":"education","lineage":["https://openalex.org/I119856527"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Hamid Jaafar","raw_affiliation_strings":["Cadi Ayyad University"],"affiliations":[{"raw_affiliation_string":"Cadi Ayyad University","institution_ids":["https://openalex.org/I119856527"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084119287","display_name":"Mounia Ab\u0131k","orcid":"https://orcid.org/0000-0002-1760-0489"},"institutions":[{"id":"https://openalex.org/I126477371","display_name":"Mohammed V University","ror":"https://ror.org/00r8w8f84","country_code":"MA","type":"education","lineage":["https://openalex.org/I126477371"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Mounia Abik","raw_affiliation_strings":["Mohammed V University"],"affiliations":[{"raw_affiliation_string":"Mohammed V University","institution_ids":["https://openalex.org/I126477371"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005008411"],"corresponding_institution_ids":["https://openalex.org/I126477371"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61417466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"19","issue":"4","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.998199999332428,"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":0.9961000084877014,"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":0.7917729616165161},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7819943428039551},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6866828203201294},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6672861576080322},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5712518692016602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5631592869758606},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.5567846298217773},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.5352412462234497},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5177140235900879},{"id":"https://openalex.org/keywords/source-text","display_name":"Source text","score":0.4726243019104004},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.29799920320510864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7917729616165161},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7819943428039551},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6866828203201294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6672861576080322},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5712518692016602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5631592869758606},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.5567846298217773},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.5352412462234497},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5177140235900879},{"id":"https://openalex.org/C120012220","wikidata":"https://www.wikidata.org/wiki/Q1754533","display_name":"Source text","level":2,"score":0.4726243019104004},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29799920320510864},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3378414","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3378414","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W108600807","https://openalex.org/W174699892","https://openalex.org/W1490960179","https://openalex.org/W1524281572","https://openalex.org/W1532342735","https://openalex.org/W1561908597","https://openalex.org/W1590009191","https://openalex.org/W1731244441","https://openalex.org/W1767292398","https://openalex.org/W1880987886","https://openalex.org/W1971220772","https://openalex.org/W1976252502","https://openalex.org/W2002019621","https://openalex.org/W2005734181","https://openalex.org/W2026665142","https://openalex.org/W2032156173","https://openalex.org/W2038721957","https://openalex.org/W2047620598","https://openalex.org/W2061272101","https://openalex.org/W2066792529","https://openalex.org/W2083160100","https://openalex.org/W2084957543","https://openalex.org/W2101210369","https://openalex.org/W2101454539","https://openalex.org/W2106593913","https://openalex.org/W2113307939","https://openalex.org/W2116555906","https://openalex.org/W2120699290","https://openalex.org/W2124807415","https://openalex.org/W2125489263","https://openalex.org/W2126807068","https://openalex.org/W2135996355","https://openalex.org/W2159719802","https://openalex.org/W2159882563","https://openalex.org/W2174542107","https://openalex.org/W2203920402","https://openalex.org/W2242292500","https://openalex.org/W2250548009","https://openalex.org/W2301416341","https://openalex.org/W2329798909","https://openalex.org/W2388245502","https://openalex.org/W2395626303","https://openalex.org/W2398936787","https://openalex.org/W2436001372","https://openalex.org/W2509876986","https://openalex.org/W2530571334","https://openalex.org/W2550821151","https://openalex.org/W2560674852","https://openalex.org/W2618735189","https://openalex.org/W2621289204","https://openalex.org/W2773853552","https://openalex.org/W2898797881","https://openalex.org/W3121623419","https://openalex.org/W4385572959"],"related_works":["https://openalex.org/W1978971213","https://openalex.org/W2398825887","https://openalex.org/W3013455799","https://openalex.org/W3090543350","https://openalex.org/W2757524561","https://openalex.org/W1517743118","https://openalex.org/W1947252915","https://openalex.org/W2807593602","https://openalex.org/W2026774655","https://openalex.org/W3015869721"],"abstract_inverted_index":{"User-generated":[0],"text":[1,53,57,76,105,226],"in":[2,23,25,32,50,77,84,103,117,207],"social":[3,78],"media":[4],"communication":[5],"(SMC)":[6],"is":[7],"mainly":[8],"characterized":[9],"by":[10,129],"non-standard":[11,95,100],"form.":[12],"It":[13],"may":[14],"contain":[15],"code":[16],"switching":[17],"(CS)":[18],"text,":[19],"a":[20,48,133,141,187,197,223],"widespread":[21],"phenomenon":[22],"SMC,":[24],"addition":[26],"to":[27,62,126,211],"noisy":[28,234],"elements":[29],"used,":[30],"especially":[31,74],"written":[33,75],"conversations":[34],"(use":[35],"of":[36,44,52,65,94,97,109,121,132,144,167,174,202,225,232],"abbreviations,":[37],"symbols,":[38],"emoticons)":[39],"or":[40],"misspelled":[41],"words.":[42,176],"All":[43,201],"these":[45,82,203],"factors":[46],"constitute":[47],"wall":[49],"front":[51],"mining":[54,58,227],"applications.":[55],"Common":[56],"tools":[59],"are":[60,205],"dedicated":[61],"standard":[63,66,98],"use":[64,96,108,131],"languages":[67,101,156],"but":[68],"cannot":[69],"deal":[70],"with":[71,106,196],"other":[72],"forms,":[73],"media.":[79],"To":[80,177],"overcome":[81],"problems,":[83],"this":[85],"work":[86],"we":[87,185,209],"present":[88],"our":[89,118,241],"solution":[90,119,218],"for":[91,190],"the":[92,107,130,151,165,179,213,230],"normalization":[93,123,166,215],"and":[99,112,154,171],"(dialects)":[102],"SMC":[104,168,233],"existent":[110],"resources":[111],"tools.":[113],"The":[114,160,236],"main":[115],"processing":[116,138,162],"consists":[120],"CS":[122],"from":[124],"multiple":[125],"one":[127],"language":[128],"machine":[134,214],"translation--like":[135],"approach.":[136],"This":[137],"relies":[139],"on":[140],"linguistic":[142],"approach":[143,189],"CS,":[145],"which":[146],"aims":[147],"at":[148],"identifying":[149],"automatically":[150],"translation":[152,193],"source":[153],"target":[155],"(without":[157],"human":[158],"intervention).":[159],"remaining":[161],"operations":[163],"concern":[164],"special":[169],"expressions":[170],"spelling":[172],"correction":[173],"out-of-vocabulary":[175],"preserve":[178],"coded-switched":[180],"sentence":[181],"meaning":[182],"across":[183],"translation,":[184],"adopt":[186],"knowledge-based":[188],"word":[191],"sense":[192],"disambiguation":[194],"reinforced":[195],"multi-lingual":[198],"vertical":[199],"context.":[200],"processes":[204],"embedded":[206],"what":[208],"refer":[210],"as":[212,222],"system.":[216],"Our":[217],"can":[219],"be":[220],"used":[221],"front-end":[224],"processing,":[228],"enabling":[229],"analysis":[231],"text.":[235],"conducted":[237],"experiments":[238],"show":[239],"that":[240],"system":[242],"performs":[243],"better":[244],"than":[245],"considered":[246],"baselines.":[247]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
