{"id":"https://openalex.org/W2912656237","doi":"https://doi.org/10.18653/v1/p19-1068","title":"MOROCO: The Moldavian and Romanian Dialectal Corpus","display_name":"MOROCO: The Moldavian and Romanian Dialectal Corpus","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2912656237","doi":"https://doi.org/10.18653/v1/p19-1068","mag":"2912656237"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1068","doi":"https://doi.org/10.18653/v1/p19-1068","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1068","pdf_url":"https://www.aclweb.org/anthology/P19-1068.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.aclweb.org/anthology/P19-1068.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030278465","display_name":"Andrei M. Butnaru","orcid":"https://orcid.org/0000-0003-3031-3203","observed_orcids":["https://orcid.org/0000-0003-3031-3203"]},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Andrei Butnaru","raw_affiliation_strings":["Department of Computer Science , University of Bucharest 14 Academiei , Bucharest , Romania","University of Bucharest, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Bucharest 14 Academiei , Bucharest , Romania","institution_ids":["https://openalex.org/I141595442"]},{"raw_affiliation_string":"University of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I141595442"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081017623","display_name":"Radu Tudor Ionescu","orcid":"https://orcid.org/0000-0002-9301-1950","observed_orcids":["https://orcid.org/0000-0002-9301-1950"]},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Radu Tudor Ionescu","raw_affiliation_strings":["Department of Computer Science , University of Bucharest 14 Academiei , Bucharest , Romania","University of Bucharest, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Bucharest 14 Academiei , Bucharest , Romania","institution_ids":["https://openalex.org/I141595442"]},{"raw_affiliation_string":"University of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I141595442"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141595442"],"apc_list":null,"apc_paid":null,"fwci":2.7736,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":{"value":0.93186102,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"688","last_page":"698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4426000118255615,"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/T10028","display_name":"Topic Modeling","score":0.4426000118255615,"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":0.26510000228881836,"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":0.13600000739097595,"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/dialect-discrimination","display_name":"dialect discrimination","score":0.414000004529953},{"id":"https://openalex.org/keywords/topic-classification","display_name":"topic classification","score":0.7059999704360962},{"id":"https://openalex.org/keywords/string-kernels","display_name":"string kernels","score":0.7829999923706055},{"id":"https://openalex.org/keywords/character-level-convolutional-neural-network","display_name":"character-level convolutional neural network","score":0.9769999980926514},{"id":"https://openalex.org/keywords/squeeze-and-excitation","display_name":"squeeze-and-excitation","score":0.8840000033378601}],"concepts":[{"id":"https://openalex.org/C129400051","wikidata":"https://www.wikidata.org/wiki/Q7913","display_name":"Romanian","level":2,"score":0.8066047430038452},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7602823972702026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7038030028343201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6161618232727051},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5825360417366028},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5568474531173706},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.532220721244812},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5094879269599915},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5045920610427856},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.49451252818107605},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4808286428451538},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.43589121103286743},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24856552481651306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12828680872917175},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p19-1068","doi":"https://doi.org/10.18653/v1/p19-1068","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1068","pdf_url":"https://www.aclweb.org/anthology/P19-1068.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1901.06543","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.06543","pdf_url":"https://arxiv.org/pdf/1901.06543","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2912656237","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1901.06543v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1901.06543","doi":"https://doi.org/10.48550/arxiv.1901.06543","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1901.06543","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1068","doi":"https://doi.org/10.18653/v1/p19-1068","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1068","pdf_url":"https://www.aclweb.org/anthology/P19-1068.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2912656237.pdf","grobid_xml":"https://content.openalex.org/works/W2912656237.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W244375653","https://openalex.org/W1480643256","https://openalex.org/W1510073064","https://openalex.org/W1560965982","https://openalex.org/W1665214252","https://openalex.org/W1832693441","https://openalex.org/W2101609803","https://openalex.org/W2109704865","https://openalex.org/W2112796928","https://openalex.org/W2125446229","https://openalex.org/W2127421665","https://openalex.org/W2153579005","https://openalex.org/W2163605009","https://openalex.org/W2170240176","https://openalex.org/W2250272113","https://openalex.org/W2250539671","https://openalex.org/W2250698219","https://openalex.org/W2251281667","https://openalex.org/W2440817164","https://openalex.org/W2552839021","https://openalex.org/W2561747913","https://openalex.org/W2573786697","https://openalex.org/W2575880437","https://openalex.org/W2620806258","https://openalex.org/W2739458769","https://openalex.org/W2741287244","https://openalex.org/W2741798456","https://openalex.org/W2752530998","https://openalex.org/W2785748711","https://openalex.org/W2794998650","https://openalex.org/W2798374729","https://openalex.org/W2799821893","https://openalex.org/W2806573136","https://openalex.org/W2806962830","https://openalex.org/W2888160543","https://openalex.org/W2899166839","https://openalex.org/W2914798463","https://openalex.org/W2951559648","https://openalex.org/W2963486098","https://openalex.org/W2963499843","https://openalex.org/W2963921497","https://openalex.org/W2963970792","https://openalex.org/W2964078312","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W4287703121","https://openalex.org/W3118502989","https://openalex.org/W3120809832","https://openalex.org/W4401042994","https://openalex.org/W4416034110","https://openalex.org/W3088204558","https://openalex.org/W2573786697","https://openalex.org/W2805957826","https://openalex.org/W3119826470","https://openalex.org/W3156186925"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,74],"introduce":[4],"the":[5,34,42,145],"Moldavian":[6,97],"and":[7,51,66,78,108,143,155],"Romanian":[8,99],"Dialectal":[9],"Corpus":[10],"(MOROCO),":[11],"which":[12],"is":[13,55],"freely":[14],"available":[15],"for":[16,60,64,70],"download":[17],"at":[18],"https://github.com/butnaruandrei/MOROCO.":[19],"The":[20],"corpus":[21],"contains":[22],"33564":[23],"samples":[24,37,59,63,69],"of":[25,41,96,149],"text":[26,100],"(with":[27],"over":[28],"10":[29],"million":[30],"tokens)":[31],"collected":[32],"from":[33],"news":[35],"domain.The":[36],"belong":[38],"to":[39,83],"one":[40],"following":[43],"six":[44],"topics:":[45],"culture,":[46],"finance,":[47],"politics,":[48],"science,":[49],"sports":[50],"tech.The":[52],"data":[53],"set":[54],"divided":[56],"into":[57],"21719":[58],"training,":[61],"5921":[62],"validation":[65],"another":[67],"5924":[68],"testing.For":[71],"each":[72],"sample,":[73],"provide":[75],"corresponding":[76],"dialectal":[77],"category":[79],"labels.This":[80],"allows":[81],"us":[82],"perform":[84,115],"empirical":[85],"studies":[86],"on":[87,122,133],"several":[88],"classification":[89],"tasks":[90],"such":[91],"as":[92,125,127],"(i)":[93],"binary":[94],"discrimination":[95],"versus":[98],"samples,":[101],"(ii)":[102],"intra-dialect":[103],"multi-class":[104,111],"categorization":[105,112],"by":[106,113],"topic":[107],"(iii)":[109],"cross-dialect":[110],"topic.We":[114],"experiments":[116],"using":[117],"a":[118,128],"shallow":[119],"approach":[120,131],"based":[121,132],"string":[123],"kernels,":[124],"well":[126],"novel":[129],"deep":[130],"character-level":[134],"convolutional":[135],"neural":[136],"networks":[137],"containing":[138],"Squeeze-and-Excitation":[139],"blocks.We":[140],"also":[141],"present":[142],"analyze":[144],"most":[146],"discriminative":[147],"features":[148],"our":[150],"best":[151],"performing":[152],"model,":[153],"before":[154],"after":[156],"named":[157],"entity":[158],"removal.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":7}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2019-02-21T00:00:00"}
