{"id":"https://openalex.org/W2729871481","doi":"https://doi.org/10.21437/interspeech.2017-1305","title":"CALYOU: A Comparable Spoken Algerian Corpus Harvested from YouTube","display_name":"CALYOU: A Comparable Spoken Algerian Corpus Harvested from YouTube","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2729871481","doi":"https://doi.org/10.21437/interspeech.2017-1305","mag":"2729871481"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1305","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5081413242","display_name":"Karima Abidi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"K. Abidi","raw_affiliation_strings":["SMarT - Statistical Machine Translation and Speech Modelization and Text (France)"],"affiliations":[{"raw_affiliation_string":"SMarT - Statistical Machine Translation and Speech Modelization and Text (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015625948","display_name":"Mohamed Amine Menacer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M.A. Menacer","raw_affiliation_strings":["SMarT - Statistical Machine Translation and Speech Modelization and Text (France)"],"affiliations":[{"raw_affiliation_string":"SMarT - Statistical Machine Translation and Speech Modelization and Text (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090778317","display_name":"Kamel Sma\u0131\u0308li","orcid":"https://orcid.org/0000-0002-4237-7303"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kamel Sma\u00efli","raw_affiliation_strings":["SMarT - Statistical Machine Translation and Speech Modelization and Text (France)"],"affiliations":[{"raw_affiliation_string":"SMarT - Statistical Machine Translation and Speech Modelization and Text (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081413242"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.7223,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.98063377,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3742","last_page":"3746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.9814000129699707,"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"}},"topics":[{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.9814000129699707,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9434000253677368,"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/T10759","display_name":"Translation Studies and Practices","score":0.9175000190734863,"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/comparability","display_name":"Comparability","score":0.9153290390968323},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.8599287271499634},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.788818359375},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.682235598564148},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6233439445495605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5616579055786133},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5564847588539124},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5092335939407349},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37794485688209534},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2516471743583679},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08829522132873535}],"concepts":[{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.9153290390968323},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.8599287271499634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788818359375},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.682235598564148},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6233439445495605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5616579055786133},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5564847588539124},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5092335939407349},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37794485688209534},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2516471743583679},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08829522132873535},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"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:10.21437/interspeech.2017-1305","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"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":0,"referenced_works":[],"related_works":["https://openalex.org/W2365594754","https://openalex.org/W2575292835","https://openalex.org/W4287902769","https://openalex.org/W3001140700","https://openalex.org/W2995453361","https://openalex.org/W3021704418","https://openalex.org/W4390295458","https://openalex.org/W1990407237","https://openalex.org/W2092282998","https://openalex.org/W2033478740"],"abstract_inverted_index":{"This":[0,25,62],"paper":[1],"addresses":[2],"the":[3,35,70,107],"issue":[4],"of":[5,7,27,32,42,64,81,106],"comparability":[6],"comments\r\nextracted":[8],"from":[9,101],"Youtube.":[10],"The":[11,48],"comments":[12],"concern":[13],"spoken\r\nAlgerian":[14],"which":[15,50],"could":[16],"be":[17,45,59],"either":[18],"local":[19],"Arabic,":[20],"Modern":[21],"Standard\r\nArabic":[22],"or":[23],"French.":[24],"diversity":[26],"expression":[28],"arises":[29],"a":[30,75,79,89,103],"huge\r\nnumber":[31],"problems":[33],"concerning":[34],"data":[36],"processing.":[37],"In":[38,73],"this\r\narticle,":[39],"several":[40],"methods":[41],"alignment":[43],"will":[44,58],"proposed":[46],"and\r\ntested.":[47],"method":[49],"permits":[51],"to":[52,67,87,96],"best":[53],"align":[54],"is":[55],"Word2Vec-based\r\napproach":[56],"that":[57],"used":[60],"iteratively.":[61],"recurrent\r\ncall":[63],"Word2Vec":[65],"allows":[66,86],"improve":[68],"significantly":[69],"results\r\nof":[71],"comparability.":[72],"fact,":[74],"dictionary-based":[76],"approach":[77,85],"leads\r\nto":[78],"Recall":[80,90],"4,":[82],"while":[83],"our":[84],"get":[88],"of\r\n33":[91],"at":[92],"rank":[93],"1.":[94],"Thanks":[95],"this":[97],"approach,":[98],"we":[99],"built":[100],"Youtube\r\nCALYOU,":[102],"Comparable":[104],"Corpus":[105],"spoken":[108],"Algerian.":[109]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
