{"id":"https://openalex.org/W2251614395","doi":"https://doi.org/10.3115/v1/w14-3602","title":"The International Corpus of Arabic: Compilation, Analysis and Evaluation","display_name":"The International Corpus of Arabic: Compilation, Analysis and Evaluation","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251614395","doi":"https://doi.org/10.3115/v1/w14-3602","mag":"2251614395"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-3602","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/w14-3602","pdf_url":null,"source":null,"license":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089945941","display_name":"Sameh Alansary","orcid":"https://orcid.org/0009-0007-2950-9555"},"institutions":[{"id":"https://openalex.org/I2802722262","display_name":"Bibliotheca Alexandrina","ror":"https://ror.org/051a9ap09","country_code":"EG","type":"archive","lineage":["https://openalex.org/I2802722262"]},{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Sameh Alansary","raw_affiliation_strings":["Department of Phonetics and Linguistics, Faculty of Arts, Alexandria University , El Shatby, Alexan-dria, Egypt","Computer and System Engineering Dept. Faculty of Engineering, Alexandria University, Alexandria Egypt","Bibliotheca Alexandrina, P.O. Box 138, 21526, El Shatby, Alexandria, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Phonetics and Linguistics, Faculty of Arts, Alexandria University , El Shatby, Alexan-dria, Egypt","institution_ids":["https://openalex.org/I84524832"]},{"raw_affiliation_string":"Computer and System Engineering Dept. Faculty of Engineering, Alexandria University, Alexandria Egypt","institution_ids":["https://openalex.org/I84524832"]},{"raw_affiliation_string":"Bibliotheca Alexandrina, P.O. Box 138, 21526, El Shatby, Alexandria, Egypt","institution_ids":["https://openalex.org/I2802722262"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108511603","display_name":"Magdy Nagi","orcid":null},"institutions":[{"id":"https://openalex.org/I2802722262","display_name":"Bibliotheca Alexandrina","ror":"https://ror.org/051a9ap09","country_code":"EG","type":"archive","lineage":["https://openalex.org/I2802722262"]},{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Magdy Nagi","raw_affiliation_strings":["Bibliotheca Alexandrina, P.O. Box 138, 21526, El Shatby, Alexandria, Egypt","Department of Phonetics and Linguistics, Faculty of Arts, Alexandria University , El Shatby, Alexan-dria, Egypt","Computer and System Engineering Dept. Faculty of Engineering, Alexandria University, Alexandria Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bibliotheca Alexandrina, P.O. Box 138, 21526, El Shatby, Alexandria, Egypt","institution_ids":["https://openalex.org/I2802722262"]},{"raw_affiliation_string":"Department of Phonetics and Linguistics, Faculty of Arts, Alexandria University , El Shatby, Alexan-dria, Egypt","institution_ids":["https://openalex.org/I84524832"]},{"raw_affiliation_string":"Computer and System Engineering Dept. Faculty of Engineering, Alexandria University, Alexandria Egypt","institution_ids":["https://openalex.org/I84524832"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5375,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91541389,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9764999747276306,"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":0.9764999747276306,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9408000111579895,"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":0.9150999784469604,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7654712796211243},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7503324747085571},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6368076205253601},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5769382119178772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.574677050113678},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.5716881155967712},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.562878429889679},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5390917658805847},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4727631211280823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34284651279449463},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2190769910812378},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09175804257392883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7654712796211243},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7503324747085571},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6368076205253601},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5769382119178772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.574677050113678},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.5716881155967712},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.562878429889679},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5390917658805847},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4727631211280823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34284651279449463},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2190769910812378},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09175804257392883},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/w14-3602","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/w14-3602","pdf_url":null,"source":null,"license":null,"license_id":null,"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:10.1.1.676.2198","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.2198","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/W14-3602.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W172005772","https://openalex.org/W651248848","https://openalex.org/W2100976324","https://openalex.org/W2126784811","https://openalex.org/W2166935132","https://openalex.org/W2279369549","https://openalex.org/W2336422109","https://openalex.org/W2594145042","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2358294942","https://openalex.org/W2620283452","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/W4403231732","https://openalex.org/W4299493485"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,89],"a":[4,37,45],"project":[5],"for":[6],"building":[7],"the":[8,33,61,72],"first":[9],"International":[10],"Corpus":[11],"of":[12,39,48],"Arabic":[13,49,64,91],"(ICA).":[14],"It":[15],"is":[16,44,57,87],"planned":[17],"to":[18,30,59],"contain":[19],"100":[20],"million":[21],"analyzed":[22,78],"tokens":[23],"with":[24,32],"an":[25],"interface":[26],"which":[27],"al-lows":[28],"users":[29],"interact":[31],"corpus":[34,47],"data":[35],"in":[36,54],"number":[38],"ways":[40],"[ICA":[41],"website].":[42],"ICA":[43,75],"representative":[46],"that":[50],"has":[51,76],"been":[52,77],"initiated":[53],"2006,":[55],"it":[56],"intended":[58],"cover":[60],"Modern":[62],"Standard":[63],"(MSA)":[65],"language":[66],"as":[67],"being":[68],"used":[69],"all":[70],"over":[71],"Arab":[73],"world.":[74],"by":[79],"Bibliotheca":[80],"Alexandrina":[81],"Morphological":[82],"Analysis":[83],"Enhancer":[84],"(BAM-AE).":[85],"BAMAE":[86],"based":[88],"Buckwalter":[90]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
