{"id":"https://openalex.org/W2068086962","doi":"https://doi.org/10.1109/aiccsa.2013.6616474","title":"Building Arabic corpora from Wikisource","display_name":"Building Arabic corpora from Wikisource","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2068086962","doi":"https://doi.org/10.1109/aiccsa.2013.6616474","mag":"2068086962"},"language":"en","primary_location":{"id":"doi:10.1109/aiccsa.2013.6616474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa.2013.6616474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 ACS International Conference on Computer Systems and Applications (AICCSA)","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/A5079157864","display_name":"Imene Bensalem","orcid":"https://orcid.org/0000-0002-2462-5967"},"institutions":[{"id":"https://openalex.org/I125485651","display_name":"Constantine 1 University","ror":"https://ror.org/017wv6808","country_code":"DZ","type":"education","lineage":["https://openalex.org/I125485651"]}],"countries":["DZ"],"is_corresponding":true,"raw_author_name":"Imene Bensalem","raw_affiliation_strings":["SCAL team, MISC laboratory, Constantine 2 University, Constantine, Algeria","MISC Lab., Constantine 2 Univ., Constantine, Algeria"],"affiliations":[{"raw_affiliation_string":"SCAL team, MISC laboratory, Constantine 2 University, Constantine, Algeria","institution_ids":["https://openalex.org/I125485651"]},{"raw_affiliation_string":"MISC Lab., Constantine 2 Univ., Constantine, Algeria","institution_ids":["https://openalex.org/I125485651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055982084","display_name":"Salim Ch\u0131kh\u0131","orcid":"https://orcid.org/0000-0002-8369-8533"},"institutions":[{"id":"https://openalex.org/I125485651","display_name":"Constantine 1 University","ror":"https://ror.org/017wv6808","country_code":"DZ","type":"education","lineage":["https://openalex.org/I125485651"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Salim Chikhi","raw_affiliation_strings":["SCAL team, MISC laboratory, Constantine 2 University, Constantine, Algeria","MISC Lab., Constantine 2 Univ., Constantine, Algeria"],"affiliations":[{"raw_affiliation_string":"SCAL team, MISC laboratory, Constantine 2 University, Constantine, Algeria","institution_ids":["https://openalex.org/I125485651"]},{"raw_affiliation_string":"MISC Lab., Constantine 2 Univ., Constantine, Algeria","institution_ids":["https://openalex.org/I125485651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053947754","display_name":"Paolo Rosso","orcid":"https://orcid.org/0000-0002-8922-1242"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Paolo Rosso","raw_affiliation_strings":["Natural Language Engineering Laboratory-EliRF, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","Natural Language Eng. Lab. - EliRF, Univ. Politec. de Valencia, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Natural Language Engineering Laboratory-EliRF, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]},{"raw_affiliation_string":"Natural Language Eng. Lab. - EliRF, Univ. Politec. de Valencia, Valencia, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079157864"],"corresponding_institution_ids":["https://openalex.org/I125485651"],"apc_list":null,"apc_paid":null,"fwci":0.9885,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82819297,"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":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9958999752998352,"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/T13629","display_name":"Text Readability and Simplification","score":0.9958999752998352,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.992900013923645,"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":0.9900000095367432,"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":0.8994314670562744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7824097871780396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6817267537117004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5954220294952393},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2172958254814148}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.8994314670562744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7824097871780396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6817267537117004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5954220294952393},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2172958254814148},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/aiccsa.2013.6616474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa.2013.6616474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 ACS International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.825.2941","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.825.2941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.dsic.upv.es/%7Eprosso/resources/BensalemEtAl_AICSSA13.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/W87733252","https://openalex.org/W1526728552","https://openalex.org/W1544505227","https://openalex.org/W2069985874","https://openalex.org/W2198207694","https://openalex.org/W6603554506","https://openalex.org/W6631530553","https://openalex.org/W6632555176","https://openalex.org/W6687525667"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,30,36],"new":[4],"tool":[5,22],"that":[6],"helps":[7],"extracting":[8],"clean":[9],"text":[10],"from":[11,32],"the":[12,27,39],"Arabic":[13,46],"Wikisource":[14],"dump":[15],"in":[16],"order":[17],"to":[18],"build":[19],"corpora.":[20],"The":[21],"purpose":[23],"is":[24,35],"illustrated":[25],"by":[26],"generation":[28],"of":[29,41],"subcorpus":[31],"Wikisource,":[33],"which":[34],"step":[37],"towards":[38],"building":[40],"an":[42],"evaluation":[43],"corpus":[44],"for":[45],"intrinsic":[47],"plagiarism":[48],"detection.":[49]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
