{"id":"https://openalex.org/W2914180170","doi":"https://doi.org/10.1093/llc/fqy074","title":"Toward Kurdish language processing: Experiments in collecting and processing the AsoSoft text corpus","display_name":"Toward Kurdish language processing: Experiments in collecting and processing the AsoSoft text corpus","publication_year":2018,"publication_date":"2018-11-14","ids":{"openalex":"https://openalex.org/W2914180170","doi":"https://doi.org/10.1093/llc/fqy074","mag":"2914180170"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fqy074","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqy074","pdf_url":null,"source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-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/A5035048262","display_name":"Hadi Veisi","orcid":"https://orcid.org/0000-0003-2372-7969"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Hadi Veisi","raw_affiliation_strings":["Faculty of New Sciences and Technologies, University of Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0003-2372-7969","affiliations":[{"raw_affiliation_string":"Faculty of New Sciences and Technologies, University of Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030850681","display_name":"Mohammad Mohammadamini","orcid":null},"institutions":[{"id":"https://openalex.org/I1516879","display_name":"Tarbiat Modares University","ror":"https://ror.org/03mwgfy56","country_code":"IR","type":"education","lineage":["https://openalex.org/I1516879"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammad MohammadAmini","raw_affiliation_strings":["IT Department, Faculty of Engineering, Tarbiat Modares University, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT Department, Faculty of Engineering, Tarbiat Modares University, Iran","institution_ids":["https://openalex.org/I1516879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018903731","display_name":"Hawre Hosseini","orcid":"https://orcid.org/0000-0002-6861-4821"},"institutions":[{"id":"https://openalex.org/I530967","display_name":"Toronto Metropolitan University","ror":"https://ror.org/05g13zd79","country_code":"CA","type":"education","lineage":["https://openalex.org/I530967"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hawre Hosseini","raw_affiliation_strings":["Electrical and Computer Engineering, Ryerson University, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Ryerson University, Canada","institution_ids":["https://openalex.org/I530967"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035048262"],"corresponding_institution_ids":["https://openalex.org/I23946033"],"apc_list":{"value":2522,"currency":"GBP","value_usd":3093},"apc_paid":null,"fwci":1.9656,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.89839123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9940000176429749,"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":0.9902999997138977,"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/perplexity","display_name":"Perplexity","score":0.9183194637298584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7734668254852295},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6936249732971191},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.6316060423851013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5825439095497131},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5494937896728516},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.52932208776474},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.5275000333786011},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4948117136955261},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.4346333146095276},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3712078928947449}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9183194637298584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734668254852295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6936249732971191},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.6316060423851013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5825439095497131},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5494937896728516},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.52932208776474},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.5275000333786011},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4948117136955261},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.4346333146095276},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3712078928947449},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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:10.1093/llc/fqy074","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqy074","pdf_url":null,"source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1574901103","https://openalex.org/W1578856370","https://openalex.org/W1579838312","https://openalex.org/W2044565013","https://openalex.org/W2104630935","https://openalex.org/W2133990480","https://openalex.org/W2141835434","https://openalex.org/W2147395478","https://openalex.org/W4249045840","https://openalex.org/W6681466998"],"related_works":["https://openalex.org/W2132221452","https://openalex.org/W2393111077","https://openalex.org/W2787311093","https://openalex.org/W1577263324","https://openalex.org/W2105076537","https://openalex.org/W2125852914","https://openalex.org/W4255406899","https://openalex.org/W2394403056","https://openalex.org/W2169518243","https://openalex.org/W1588058606"],"abstract_inverted_index":{"In":[0,85],"this":[1,166],"article,":[2],"we":[3,92],"introduce":[4],"the":[5,36,45,90,106,125,133,142,149,152],"first":[6,150],"Kurdish":[7,12,19,43,49,135,159,179],"text":[8,17,52,136],"corpus":[9,53,73,107],"for":[10,157,182],"Central":[11,42,134,158,178],"(Sorani)":[13],"branch,":[14],"called":[15],"AsoSoft":[16,51],"corpus.":[18],"language,":[20],"which":[21],"is":[22,44,54,108,160,168,180],"spoken":[23],"by":[24],"more":[25],"than":[26],"30":[27],"million":[28,58],"people,":[29],"has":[30,61,74,120],"various":[31],"dialects.":[32],"As":[33],"one":[34],"of":[35,40,48,55,105,127,132,144,154,165,177],"two":[37],"main":[38],"branches":[39],"Kurdish,":[41],"formal":[46],"dialect":[47],"literature.":[50],"size":[56],"188":[57],"tokens":[59],"and":[60,70,77,88,97,115,162],"been":[62,75,121],"collected":[63],"mostly":[64],"from":[65],"Web":[66],"sites,":[67],"published":[68],"books,":[69],"magazines.":[71],"The":[72,129,175],"normalized":[76],"converted":[78],"into":[79],"Text":[80],"Encoding":[81],"Initiative":[82],"XML":[83],"format.":[84],"both":[86],"collecting":[87],"processing":[89,137],"text,":[91],"have":[93,98],"faced":[94],"several":[95],"challenges":[96],"proposed":[99],"solutions":[100],"to":[101,123],"them.":[102],"About":[103],"22%":[104],"topic":[109,113,117],"annotated":[110],"with":[111,141],"six":[112],"tags,":[114],"a":[116,183],"identification":[118],"task":[119],"done":[122],"evaluate":[124],"correctness":[126],"annotation.":[128],"computational":[130],"experiments":[131],"are":[138],"also":[139,163],"presented":[140,161],"support":[143],"related":[145],"supplementary":[146],"statistics.":[147],"For":[148],"time,":[151],"validity":[153],"Zipf\u2019s":[155],"law":[156],"perplexity":[164,176],"language":[167,173,185],"calculated":[169],"using":[170],"standard":[171],"N-gram":[172],"models.":[174],"276":[181],"tri-gram":[184],"model.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}