{"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","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":null,"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"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","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"},"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":true,"raw_author_name":"Andrei Butnaru","raw_affiliation_strings":["Department of Computer Science, University of Bucharest 14 Academiei, Bucharest, Romania","University of Bucharest, Bucharest, Romania"],"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"},"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"],"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":2,"corresponding_author_ids":["https://openalex.org/A5030278465"],"corresponding_institution_ids":["https://openalex.org/I141595442"],"apc_list":null,"apc_paid":null,"fwci":0.46085324,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69395237,"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":"688","last_page":"698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9965999722480774,"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.9580000042915344,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/romanian","display_name":"Romanian","score":0.8066047430038452},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7602823972702026},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7038030028343201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6161618232727051},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5825360417366028},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5568474531173706},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.532220721244812},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5094879269599915},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5045920610427856},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.49451252818107605},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4808286428451538},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.43589121103286743},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24856552481651306},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12828680872917175}],"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","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":null,"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","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":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:2912656237","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":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","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":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi: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":null,"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":[{"display_name":"Reduced inequalities","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":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/W1938755728","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/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/W2741287244","https://openalex.org/W2741798456","https://openalex.org/W2752530998","https://openalex.org/W2785748711","https://openalex.org/W2794998650","https://openalex.org/W2806573136","https://openalex.org/W2806962830","https://openalex.org/W2888160543","https://openalex.org/W2899166839","https://openalex.org/W2914798463","https://openalex.org/W2963012544","https://openalex.org/W2963486098","https://openalex.org/W2963499843","https://openalex.org/W2963830885","https://openalex.org/W2963842834","https://openalex.org/W2963921497","https://openalex.org/W2963970792","https://openalex.org/W2964078312","https://openalex.org/W2964121744","https://openalex.org/W2964335814"],"related_works":["https://openalex.org/W2963586344","https://openalex.org/W3016397003","https://openalex.org/W3016021175","https://openalex.org/W3012069291","https://openalex.org/W3185522793","https://openalex.org/W2734322117","https://openalex.org/W2250921181","https://openalex.org/W3201750410","https://openalex.org/W2809532654","https://openalex.org/W3032726725","https://openalex.org/W2971309218","https://openalex.org/W2897077948","https://openalex.org/W1445897916","https://openalex.org/W2492906955","https://openalex.org/W2527844536","https://openalex.org/W2970578875","https://openalex.org/W3152729570","https://openalex.org/W2752413581","https://openalex.org/W1990655767","https://openalex.org/W2620524555"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,77],"introduce":[4],"the":[5,34,43,151],"MOldavian":[6],"and":[7,52,68,81,112,149,161],"ROmanian":[8],"Dialectal":[9],"COrpus":[10],"(MOROCO),":[11],"which":[12],"is":[13,57],"freely":[14],"available":[15],"for":[16,62,66,72],"download":[17],"at":[18],"https://github.com/butnaruandrei/MOROCO.":[19],"The":[20,37,54],"corpus":[21],"contains":[22],"33564":[23],"samples":[24,38,61,65,71],"of":[25,42,100,155],"text":[26,104],"(with":[27],"over":[28],"10":[29],"million":[30],"tokens)":[31],"collected":[32],"from":[33],"news":[35],"domain.":[36],"belong":[39],"to":[40,87],"one":[41],"following":[44],"six":[45],"topics:":[46],"culture,":[47],"finance,":[48],"politics,":[49],"science,":[50],"sports":[51],"tech.":[53],"data":[55],"set":[56],"divided":[58],"into":[59],"21719":[60],"training,":[63],"5921":[64],"validation":[67],"another":[69],"5924":[70],"testing.":[73],"For":[74],"each":[75],"sample,":[76],"provide":[78],"corresponding":[79],"dialectal":[80],"category":[82],"labels.":[83],"This":[84],"allows":[85],"us":[86],"perform":[88,120],"empirical":[89],"studies":[90],"on":[91,127,138],"several":[92],"classification":[93],"tasks":[94],"such":[95],"as":[96,130,132],"(i)":[97],"binary":[98],"discrimination":[99],"Moldavian":[101],"versus":[102],"Romanian":[103],"samples,":[105],"(ii)":[106],"intra-dialect":[107],"multi-class":[108,115],"categorization":[109,116],"by":[110,117],"topic":[111],"(iii)":[113],"cross-dialect":[114],"topic.":[118],"We":[119,146],"experiments":[121],"using":[122],"a":[123,133],"shallow":[124],"approach":[125,136],"based":[126,137],"string":[128],"kernels,":[129],"well":[131],"novel":[134],"deep":[135],"character-level":[139],"convolutional":[140],"neural":[141],"networks":[142],"containing":[143],"Squeeze-and-Excitation":[144],"blocks.":[145],"also":[147],"present":[148],"analyze":[150],"most":[152],"discriminative":[153],"features":[154],"our":[156],"best":[157],"performing":[158],"model,":[159],"before":[160],"after":[162],"named":[163],"entity":[164],"removal.":[165]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}