{"id":"https://openalex.org/W2250212502","doi":"https://doi.org/10.3115/v1/w14-3612","title":"Transliteration of Arabizi into Arabic Orthography: Developing a Parallel Annotated Arabizi-Arabic Script SMS/Chat Corpus","display_name":"Transliteration of Arabizi into Arabic Orthography: Developing a Parallel Annotated Arabizi-Arabic Script SMS/Chat Corpus","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250212502","doi":"https://doi.org/10.3115/v1/w14-3612","mag":"2250212502"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-3612","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3612","pdf_url":"https://aclanthology.org/W14-3612.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-3612.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025999439","display_name":"Ann Bies","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ann Bies","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059816941","display_name":"Zhiyi Song","orcid":"https://orcid.org/0000-0002-6060-0353"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyi Song","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053026044","display_name":"Mohamed Maamouri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Maamouri","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082669942","display_name":"Stephen Grimes","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Grimes","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080251436","display_name":"Haejoong Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haejoong Lee","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103379830","display_name":"Jonathan Wright","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Wright","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004510221","display_name":"Stephanie Strassel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephanie Strassel","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Habash","orcid":"https://orcid.org/0000-0002-1831-3457"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nizar Habash","raw_affiliation_strings":["Computer Science Department, New York University Abu Dhabi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, New York University Abu Dhabi","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060938475","display_name":"Ramy Eskander","orcid":null},"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":"Ramy Eskander","raw_affiliation_strings":["Center for Computational Learning Systems, Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Learning Systems, Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021314411","display_name":"Owen Rambow","orcid":null},"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":"Owen Rambow","raw_affiliation_strings":["Center for Computational Learning Systems, Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Learning Systems, Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4978,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.95971725,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.996399998664856,"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":0.9876999855041504,"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/transliteration","display_name":"Transliteration","score":0.9028209447860718},{"id":"https://openalex.org/keywords/orthography","display_name":"Orthography","score":0.8371610641479492},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7539501190185547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6283793449401855},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.5425544381141663},{"id":"https://openalex.org/keywords/wright","display_name":"Wright","score":0.5077050924301147},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5046323537826538},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4428901672363281},{"id":"https://openalex.org/keywords/romanization","display_name":"Romanization","score":0.4270133078098297},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4089367985725403},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10659554600715637},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07240733504295349}],"concepts":[{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.9028209447860718},{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.8371610641479492},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7539501190185547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6283793449401855},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.5425544381141663},{"id":"https://openalex.org/C2777667586","wikidata":"https://www.wikidata.org/wiki/Q8038170","display_name":"Wright","level":2,"score":0.5077050924301147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5046323537826538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4428901672363281},{"id":"https://openalex.org/C106930687","wikidata":"https://www.wikidata.org/wiki/Q976327","display_name":"Romanization","level":2,"score":0.4270133078098297},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4089367985725403},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10659554600715637},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07240733504295349},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/w14-3612","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3612","pdf_url":"https://aclanthology.org/W14-3612.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.676.4146","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.4146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-3612.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-3612","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3612","pdf_url":"https://aclanthology.org/W14-3612.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250212502.pdf","grobid_xml":"https://content.openalex.org/works/W2250212502.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W131663347","https://openalex.org/W162697342","https://openalex.org/W408046128","https://openalex.org/W1544567521","https://openalex.org/W1573344341","https://openalex.org/W1728658630","https://openalex.org/W1966863499","https://openalex.org/W2032355794","https://openalex.org/W2090362702","https://openalex.org/W2104463314","https://openalex.org/W2109704865","https://openalex.org/W2138738738","https://openalex.org/W2153848201","https://openalex.org/W2157765050","https://openalex.org/W2166660646","https://openalex.org/W2183864645","https://openalex.org/W2250414785","https://openalex.org/W2250792670","https://openalex.org/W2250816155","https://openalex.org/W2250868350","https://openalex.org/W2250967669","https://openalex.org/W2251092354","https://openalex.org/W2338181011","https://openalex.org/W2432289224","https://openalex.org/W2729906263","https://openalex.org/W2913739034","https://openalex.org/W4233787372"],"related_works":["https://openalex.org/W4389731935","https://openalex.org/W4402657567","https://openalex.org/W4377080406","https://openalex.org/W2808928361","https://openalex.org/W4389684388","https://openalex.org/W2522857523","https://openalex.org/W2729795264","https://openalex.org/W2395524355","https://openalex.org/W4387031027","https://openalex.org/W922362645"],"abstract_inverted_index":{"Ann":[0],"Bies,":[1],"Zhiyi":[2],"Song,":[3],"Mohamed":[4],"Maamouri,":[5],"Stephen":[6],"Grimes,":[7],"Haejoong":[8],"Lee,":[9],"Jonathan":[10],"Wright,":[11],"Stephanie":[12],"Strassel,":[13],"Nizar":[14],"Habash,":[15],"Ramy":[16],"Eskander,":[17],"Owen":[18],"Rambow.":[19],"Proceedings":[20],"of":[21],"the":[22],"EMNLP":[23],"2014":[24],"Workshop":[25],"on":[26],"Arabic":[27],"Natural":[28],"Language":[29],"Processing":[30],"(ANLP).":[31],"2014.":[32]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
