{"id":"https://openalex.org/W137260243","doi":"https://doi.org/10.7916/d8np2dqz","title":"CODACT: Towards Identifying Orthographic Variants in Dialectal Arabic","display_name":"CODACT: Towards Identifying Orthographic Variants in Dialectal Arabic","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W137260243","doi":"https://doi.org/10.7916/d8np2dqz","mag":"137260243"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.845","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/I/I11/I11-1036.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7916/d8np2dqz","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029074038","display_name":"Pradeep Dasigi","orcid":"https://orcid.org/0000-0001-7127-1316","observed_orcids":["https://orcid.org/0000-0001-7127-1316"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dasigi, Pradeep","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038581447","display_name":"Mona Diab","orcid":"https://orcid.org/0000-0002-7696-1436","observed_orcids":["https://orcid.org/0000-0002-7696-1436"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diab, Mona","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":2.0627,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87922366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"318","last_page":"326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.98580002784729,"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":0.98580002784729,"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.004000000189989805,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/arabic-dialects","display_name":"Arabic dialects","score":0.9850000143051147},{"id":"https://openalex.org/keywords/orthographic-variants","display_name":"orthographic variants","score":0.9549999833106995},{"id":"https://openalex.org/keywords/spelling-normalization","display_name":"spelling normalization","score":0.7590000033378601},{"id":"https://openalex.org/keywords/unsupervised-clustering","display_name":"unsupervised clustering","score":0.7860000133514404},{"id":"https://openalex.org/keywords/string-similarity","display_name":"string similarity","score":0.7350000143051147},{"id":"https://openalex.org/keywords/egyptian-arabic","display_name":"Egyptian Arabic","score":0.9120000004768372},{"id":"https://openalex.org/keywords/levantine-arabic","display_name":"Levantine Arabic","score":0.9990000128746033},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.6779999732971191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106129169464111},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7015559673309326},{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.6759214997291565},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.6474345326423645},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.62821364402771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6198936104774475},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4652937650680542},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4432838559150696},{"id":"https://openalex.org/C91304198","wikidata":"https://www.wikidata.org/wiki/Q9288","display_name":"Hebrew","level":2,"score":0.4253411293029785},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4216669499874115},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.295260488986969},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.845","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/I/I11/I11-1036.pdf","raw_type":"text"},{"id":"doi:10.7916/d8np2dqz","doi":"https://doi.org/10.7916/d8np2dqz","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8np2dqz","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:137260243","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/I11-1036.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420006","display_name":"International Joint Conference on Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 Joint Conference on Natural Language Processing","raw_type":null}],"best_oa_location":{"id":"doi:10.7916/d8np2dqz","doi":"https://doi.org/10.7916/d8np2dqz","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8np2dqz","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W1972099155","https://openalex.org/W2075847275","https://openalex.org/W2087962968","https://openalex.org/W2147411813","https://openalex.org/W2149709850","https://openalex.org/W2164937289","https://openalex.org/W2166555323","https://openalex.org/W3198160809"],"related_works":["https://openalex.org/W4402671205","https://openalex.org/W4206850324","https://openalex.org/W7135914746","https://openalex.org/W3166103216","https://openalex.org/W6973633513","https://openalex.org/W2250414785","https://openalex.org/W2978948973","https://openalex.org/W7096078399","https://openalex.org/W2137498753","https://openalex.org/W3191380211"],"abstract_inverted_index":{"Dialectal":[0],"Arabic":[1,19,34,184],"(DA)":[2],"is":[3,13,45,56,111,164],"the":[4,16,52,93,112,139,165,170,192,237],"spoken":[5],"vernacular":[6],"for":[7,33,37,59,172,197,221,225,234],"over":[8],"300M":[9],"people":[10],"worldwide.":[11],"DA":[12,66,96],"emerging":[14],"as":[15,119],"form":[17],"of":[18,95,141,183,195],"written":[20,86],"in":[21,64,87,126,145,180,217,229],"online":[22],"communication:":[23],"chats,":[24],"emails,":[25],"blogs,":[26],"etc.":[27],"However,":[28],"most":[29],"existing":[30],"NLP":[31],"tools":[32],"are":[35,176],"designed":[36],"processing":[38,94],"Modern":[39],"Standard":[40],"Arabic,":[41],"a":[42,57,76,82,127,214],"variety":[43],"that":[44,55,74,137,152],"more":[46],"formal":[47],"and":[48,79,156,187,204,223,227],"scripted.":[49],"Apart":[50],"from":[51,236],"genre":[53],"variation":[54],"hindrance":[58],"any":[60],"language":[61],"processing,":[62],"even":[63],"English,":[65],"has":[67,75],"no":[68],"orthographic":[69,143],"standard,":[70],"compared":[71],"to":[72,106,122,200,207],"MSA":[73],"standard":[77],"orthography":[78],"script.":[80],"Accordingly,":[81],"word":[83],"may":[84],"be":[85,107],"many":[88],"possible":[89],"inconsistent":[90],"spellings":[91],"rendering":[92],"very":[97],"challenging.":[98],"To":[99,160],"solve":[100],"this":[101,117,163],"problem,":[102,118],"such":[103],"inconsistencies":[104],"have":[105],"normalized.":[108],"This":[109,212],"work":[110],"\ufb01rst":[113,166],"step":[114],"towards":[115],"addressing":[116],"we":[120],"attempt":[121,167],"identify":[123],"spelling":[124],"variants":[125,144],"given":[128],"textual":[129],"document.":[130],"We":[131,147],"present":[132],"an":[133],"unsupervised":[134],"clustering":[135],"approach":[136],"addresses":[138],"problem":[140,171],"identifying":[142],"DA.":[146,173],"employ":[148],"different":[149],"similarity":[150,155],"measures":[151],"exploit":[153],"string":[154],"contextual":[157],"semantic":[158],"similarity.":[159],"our":[161],"knowledge":[162],"at":[168],"solving":[169],"Our":[174,189],"approaches":[175],"tested":[177],"on":[178],"data":[179],"two":[181],"dialects":[182],"-":[185],"Egyptian":[186,198,222],"Levantine.":[188],"system":[190],"achieves":[191],"highest":[193],"Entropy":[194],"0.19":[196],"(corresponding":[199,206],"68%":[201],"cluster":[202,209,230],"precision)":[203,210],"Levantine":[205],"64%":[208],"respectively.":[211],"constitutes":[213],"signi\ufb01cant":[215],"reduction":[216],"entropy":[218],"(from":[219,232],"0.47":[220],"0.51":[224],"Levantine)":[226],"improvement":[228],"precision":[231],"29%":[233],"both)":[235],"baseline.":[238]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2016-06-24T00:00:00"}