{"id":"https://openalex.org/W2115295410","doi":"https://doi.org/10.3115/v1/w14-5313","title":"Improved Sentence-Level Arabic Dialect Classification","display_name":"Improved Sentence-Level Arabic Dialect Classification","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2115295410","doi":"https://doi.org/10.3115/v1/w14-5313","mag":"2115295410"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-5313","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5313","pdf_url":"https://aclanthology.org/W14-5313.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 First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-5313.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001253909","display_name":"Christoph Tillmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christoph Tillmann","raw_affiliation_strings":["IBM, ,"],"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070002963","display_name":"Saab Mansour","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Saab Mansour","raw_affiliation_strings":["[Rwth Aachen University]"],"affiliations":[{"raw_affiliation_string":"[Rwth Aachen University]","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079875307","display_name":"Yaser Al-Onaizan","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaser Al-Onaizan","raw_affiliation_strings":["IBM, ,"],"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001253909"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":6.3594,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":{"value":0.96586206,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"110","last_page":"119"},"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/T12380","display_name":"Authorship Attribution and Profiling","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/T10028","display_name":"Topic Modeling","score":0.9965000152587891,"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/arabic","display_name":"Arabic","score":0.8018015623092651},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7878403663635254},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7707540988922119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7259746789932251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6857371926307678},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5931161642074585},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5804412364959717},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.5227001905441284},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5223049521446228},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4466891586780548},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41245460510253906},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11050093173980713}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.8018015623092651},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7878403663635254},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7707540988922119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259746789932251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6857371926307678},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5931161642074585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5804412364959717},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.5227001905441284},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5223049521446228},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4466891586780548},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41245460510253906},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11050093173980713},{"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:10.3115/v1/w14-5313","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5313","pdf_url":"https://aclanthology.org/W14-5313.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 First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-5313","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5313","pdf_url":"https://aclanthology.org/W14-5313.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 First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G1946722460","display_name":null,"funder_award_id":"HR0011-12-C-0015","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2115295410.pdf","grobid_xml":"https://content.openalex.org/works/W2115295410.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W244375653","https://openalex.org/W968157591","https://openalex.org/W1533946607","https://openalex.org/W1848260265","https://openalex.org/W1951381097","https://openalex.org/W1975879668","https://openalex.org/W2008652694","https://openalex.org/W2097341304","https://openalex.org/W2106595396","https://openalex.org/W2107564089","https://openalex.org/W2117238933","https://openalex.org/W2118585731","https://openalex.org/W2137387514","https://openalex.org/W2137698233","https://openalex.org/W2163361328","https://openalex.org/W2165966284","https://openalex.org/W2250174871","https://openalex.org/W2251986002","https://openalex.org/W2533388221","https://openalex.org/W2778791957"],"related_works":["https://openalex.org/W2620283452","https://openalex.org/W4392318734","https://openalex.org/W4322750817","https://openalex.org/W4400896925","https://openalex.org/W2801712537","https://openalex.org/W4396221470","https://openalex.org/W587642979","https://openalex.org/W2894059694","https://openalex.org/W4299493485","https://openalex.org/W589191641"],"abstract_inverted_index":{"The":[0],"paper":[1],"presents":[2],"work":[3],"on":[4,22,44,61,93],"improved":[5],"sentence-level":[6],"dialect":[7,94],"classification":[8,115],"of":[9,34,58,110],"Egyptian":[10],"Arabic":[11,16,63],"(ARZ)":[12],"vs.":[13],"Modern":[14],"Standard":[15],"(MSA).":[17],"Our":[18,52],"approach":[19],"is":[20],"based":[21,43],"binary":[23],"feature":[24],"functions":[25],"that":[26,104],"can":[27],"be":[28],"implemented":[29],"with":[30],"a":[31,39,45,77,111],"minimal":[32],"amount":[33],"task-specific":[35],"knowledge.":[36],"We":[37,88],"train":[38],"featurerich":[40],"linear":[41,46],"classifier":[42,92],"support-vector":[47],"machine":[48],"(linear":[49],"SVM)":[50],"approach.":[51],"best":[53],"system":[54],"achieves":[55],"an":[56,97],"accuracy":[57,81,116],"89.1":[59],"%":[60,79],"the":[62,84,91,108],"Online":[64],"Commentary":[65],"(AOC)":[66],"dataset":[67],"(Zaidan":[68],"and":[69],"Callison-Burch,":[70],"2011)":[71],"using":[72],"10-fold":[73],"stratified":[74],"cross":[75],"validation:":[76],"1.3":[78],"absolute":[80],"improvement":[82],"over":[83],"results":[85],"published":[86],"by":[87],"also":[89],"evaluate":[90],"data":[95,99],"from":[96],"additional":[98],"source.":[100],"Here,":[101],"we":[102],"find":[103],"features":[105],"which":[106],"measure":[107],"informalness":[109],"sentence":[112],"actually":[113],"decrease":[114],"significantly.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}