{"id":"https://openalex.org/W2970345257","doi":"https://doi.org/10.18653/v1/w19-4616","title":"Construction and Annotation of the Jordan Comprehensive Contemporary Arabic Corpus (JCCA)","display_name":"Construction and Annotation of the Jordan Comprehensive Contemporary Arabic Corpus (JCCA)","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970345257","doi":"https://doi.org/10.18653/v1/w19-4616","mag":"2970345257"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4616","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4616","pdf_url":"https://www.aclweb.org/anthology/W19-4616.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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4616.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051850429","display_name":"Majdi Sawalha","orcid":"https://orcid.org/0000-0003-4975-6709"},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]},{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE","JO"],"is_corresponding":true,"raw_author_name":"Majdi Sawalha","raw_affiliation_strings":["University of Jordan, Jordan Universitt Leipzig, Germany","University of Jordan, Jordan Universit\u00e4t Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"University of Jordan, Jordan Universitt Leipzig, Germany","institution_ids":["https://openalex.org/I114972647"]},{"raw_affiliation_string":"University of Jordan, Jordan Universit\u00e4t Leipzig, Germany","institution_ids":["https://openalex.org/I114972647","https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090694041","display_name":"Faisal Alshargi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Faisal Alshargi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090571215","display_name":"Abdallah Alshdaifat","orcid":"https://orcid.org/0000-0002-9692-3242"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]},{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["DE","JO"],"is_corresponding":false,"raw_author_name":"Abdallah AlShdaifat","raw_affiliation_strings":["University of Jordan, Jordan Universitt Leipzig, Germany","University of Jordan, Jordan Universit\u00e4t Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"University of Jordan, Jordan Universitt Leipzig, Germany","institution_ids":["https://openalex.org/I114972647"]},{"raw_affiliation_string":"University of Jordan, Jordan Universit\u00e4t Leipzig, Germany","institution_ids":["https://openalex.org/I114972647","https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037502713","display_name":"Sane Yagi","orcid":"https://orcid.org/0000-0002-0594-3230"},"institutions":[{"id":"https://openalex.org/I29891158","display_name":"University of Sharjah","ror":"https://ror.org/00engpz63","country_code":"AE","type":"education","lineage":["https://openalex.org/I29891158"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Sane Yagi","raw_affiliation_strings":["University of Sharjah, UAE"],"affiliations":[{"raw_affiliation_string":"University of Sharjah, UAE","institution_ids":["https://openalex.org/I29891158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000233309","display_name":"Mohammad Ayed Qudah","orcid":null},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]},{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["DE","JO"],"is_corresponding":false,"raw_author_name":"Mohammad A. Qudah","raw_affiliation_strings":["University of Jordan, Jordan Universitt Leipzig, Germany","University of Jordan, Jordan Universit\u00e4t Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"University of Jordan, Jordan Universitt Leipzig, Germany","institution_ids":["https://openalex.org/I114972647"]},{"raw_affiliation_string":"University of Jordan, Jordan Universit\u00e4t Leipzig, Germany","institution_ids":["https://openalex.org/I114972647","https://openalex.org/I926574661"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051850429"],"corresponding_institution_ids":["https://openalex.org/I114972647","https://openalex.org/I926574661"],"apc_list":null,"apc_paid":null,"fwci":0.4201,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71008635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"148","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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":0.9962999820709229,"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":0.991100013256073,"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/T13959","display_name":"Swearing, Euphemism, Multilingualism","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.748408854007721},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6777063012123108},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6323513388633728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5862261056900024},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.555172860622406},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.5517234802246094},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.5252587199211121},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5130056738853455},{"id":"https://openalex.org/keywords/british-national-corpus","display_name":"British National Corpus","score":0.4893035590648651},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4759899377822876},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.4488721191883087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748408854007721},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6777063012123108},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6323513388633728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5862261056900024},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.555172860622406},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.5517234802246094},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.5252587199211121},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5130056738853455},{"id":"https://openalex.org/C2776725116","wikidata":"https://www.wikidata.org/wiki/Q236935","display_name":"British National Corpus","level":2,"score":0.4893035590648651},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4759899377822876},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.4488721191883087},{"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:10.18653/v1/w19-4616","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4616","pdf_url":"https://www.aclweb.org/anthology/W19-4616.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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4616","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4616","pdf_url":"https://www.aclweb.org/anthology/W19-4616.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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970345257.pdf","grobid_xml":"https://content.openalex.org/works/W2970345257.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W122202277","https://openalex.org/W140145567","https://openalex.org/W156229664","https://openalex.org/W162142708","https://openalex.org/W179850243","https://openalex.org/W183724032","https://openalex.org/W1205555590","https://openalex.org/W1558584194","https://openalex.org/W1600700896","https://openalex.org/W1608382592","https://openalex.org/W1981685568","https://openalex.org/W2013069143","https://openalex.org/W2015930392","https://openalex.org/W2047372085","https://openalex.org/W2056054925","https://openalex.org/W2074488411","https://openalex.org/W2085759086","https://openalex.org/W2103164428","https://openalex.org/W2118559137","https://openalex.org/W2172057406","https://openalex.org/W2250358209","https://openalex.org/W2250816155","https://openalex.org/W2251614395","https://openalex.org/W2396324390","https://openalex.org/W2560280095","https://openalex.org/W2572275374","https://openalex.org/W2594145042","https://openalex.org/W2600338664","https://openalex.org/W2614620964","https://openalex.org/W2622811201","https://openalex.org/W2741553309","https://openalex.org/W2967147451","https://openalex.org/W4210348152","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2794113965","https://openalex.org/W300344534","https://openalex.org/W3096124370","https://openalex.org/W4388119661","https://openalex.org/W4380575491","https://openalex.org/W1587508994","https://openalex.org/W4315484253","https://openalex.org/W2907907821","https://openalex.org/W2237015346","https://openalex.org/W3046712000"],"abstract_inverted_index":{"To":[0],"compile":[1],"a":[2,25,68,79,155,163,174],"modern":[3],"dictionary":[4],"that":[5,30,71,177],"catalogues":[6],"the":[7,17,35,49,54,73,84,117,122,125,134,138,159,187,197,202],"words":[8],"in":[9,16,51,101,112,120],"currency,":[10],"and":[11,63,92,99,141,148,184,189,194],"to":[12,23,45,87,153],"study":[13],"linguistic":[14],"patterns":[15,191],"contemporary":[18,95],"language,":[19],"it":[20,171],"is":[21,86,130,162,178],"necessary":[22],"have":[24],"corpus":[26,70,85,198],"of":[27,34,48,53,56,83,94,133,143,158,192,206],"authentic":[28],"texts":[29],"reflect":[31],"current":[32],"usage":[33],"language.":[36],"Although":[37],"there":[38],"are":[39],"numerous":[40],"Arabic":[41,96,182],"corpora,":[42],"none":[43],"claims":[44],"be":[46,88,107],"representative":[47,93],"language":[50],"terms":[52],"combination":[55],"geographical":[57],"region,":[58],"genre,":[59],"subject":[60],"matter,":[61],"mode,":[62],"medium.":[64],"This":[65],"paper":[66,129],"describes":[67],"100-million-word":[69],"takes":[72],"British":[74],"National":[75],"Corpus":[76],"(BNC)":[77],"as":[78,97],"model.":[80],"The":[81],"aim":[82],"balanced,":[89],"annotated,":[90],"comprehensive,":[91],"written":[98],"spoken":[100,204],"Arab":[102],"countries":[103],"today.":[104],"It":[105],"will":[106],"different":[108],"from":[109],"most":[110],"others":[111],"not":[113],"being":[114],"heavily-dominated":[115],"by":[116,172,185],"news":[118],"or":[119],"mixing":[121],"classical":[123],"with":[124],"modern.":[126],"In":[127],"this":[128,144],"an":[131],"outline":[132],"methodology":[135],"adopted":[136],"for":[137],"design,":[139],"construction,":[140],"annotation":[142,166],"corpus.":[145,160],"DIWAN":[146],"(Al-Shargi":[147],"Rambow,":[149],"2015)":[150],"was":[151],"used":[152],"annotate":[154],"one-million-word":[156],"snapshot":[157],"DI-WAN":[161],"dialectal":[164],"word":[165],"tool,":[167],"but":[168],"we":[169,199],"upgraded":[170],"adding":[173,186],"new":[175],"tag-set":[176],"based":[179],"on":[180],"traditional":[181],"grammar":[183],"roots":[188],"morphological":[190],"nouns":[193],"verbs.":[195],"Moreover,":[196],"constructed":[200],"covers":[201],"major":[203],"varieties":[205],"Arabic.":[207]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
