{"id":"https://openalex.org/W4282018267","doi":"https://doi.org/10.48550/arxiv.2206.02421","title":"MorisienMT: A Dataset for Mauritian Creole Machine Translation","display_name":"MorisienMT: A Dataset for Mauritian Creole Machine Translation","publication_year":2022,"publication_date":"2022-06-06","ids":{"openalex":"https://openalex.org/W4282018267","doi":"https://doi.org/10.48550/arxiv.2206.02421"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2206.02421","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.02421","pdf_url":"https://arxiv.org/pdf/2206.02421","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.02421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077362985","display_name":"Raj Dabre","orcid":"https://orcid.org/0000-0003-0664-3421","observed_orcids":["https://orcid.org/0000-0003-0664-3421"]},"institutions":[{"id":"https://openalex.org/I69072986","display_name":"University of Mauritius","ror":"https://ror.org/05cyprz33","country_code":"MU","type":"education","lineage":["https://openalex.org/I69072986"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP","MU"],"is_corresponding":false,"raw_author_name":"Dabre, Raj","raw_affiliation_strings":["Aneerav Sukhoo University of Mauritius , Mauritius","NICT , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aneerav Sukhoo University of Mauritius , Mauritius","institution_ids":["https://openalex.org/I69072986"]},{"raw_affiliation_string":"NICT , Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058987991","display_name":"Aneerav Sukhoo","orcid":"https://orcid.org/0000-0002-4077-0611","observed_orcids":["https://orcid.org/0000-0002-4077-0611"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sukhoo, Aneerav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9970999956130981,"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":0.9970999956130981,"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":0.0015999999595806003,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0006000000284984708,"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/mauritian-creole","display_name":"Mauritian Creole","score":0.9789999723434448},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.9290000200271606},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.8330000042915344},{"id":"https://openalex.org/keywords/monolingual-corpora","display_name":"monolingual corpora","score":0.9879999756813049},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7540000081062317},{"id":"https://openalex.org/keywords/creole-languages","display_name":"creole languages","score":0.7020000219345093}],"concepts":[{"id":"https://openalex.org/C174613046","wikidata":"https://www.wikidata.org/wiki/Q33289","display_name":"Creole language","level":2,"score":0.8557766675949097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6794248819351196},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6765758395195007},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6339244842529297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6190460920333862},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6176738739013672},{"id":"https://openalex.org/C159789966","wikidata":"https://www.wikidata.org/wiki/Q80839","display_name":"Lingua franca","level":2,"score":0.5927080512046814},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5445951223373413},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4509836435317993},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4387325942516327},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.42520591616630554},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06144601106643677},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2206.02421","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.02421","pdf_url":"https://arxiv.org/pdf/2206.02421","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":"doi:10.48550/arxiv.2206.02421","doi":"https://doi.org/10.48550/arxiv.2206.02421","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.02421","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.02421","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.02421","pdf_url":"https://arxiv.org/pdf/2206.02421","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4404783810","https://openalex.org/W7163374232","https://openalex.org/W4407339064","https://openalex.org/W4416033767","https://openalex.org/W2786396263","https://openalex.org/W2006792905","https://openalex.org/W4396821967","https://openalex.org/W7202119570","https://openalex.org/W7099559322","https://openalex.org/W2161044793"],"abstract_inverted_index":{"In":[0],"this":[1,111],"paper,":[2],"we":[3,79],"describe":[4,62],"MorisienMT,":[5],"a":[6,30,37,48,81],"dataset":[7],"for":[8,51,97,105,114],"benchmarking":[9],"machine":[10,116],"translation":[11],"quality":[12],"of":[13,23,26,36,58,83],"Mauritian":[14,16],"Creole.":[15],"Creole":[17],"(Morisien)":[18],"is":[19,29],"the":[20,24,63,68,73,87],"lingua":[21],"franca":[22],"Republic":[25],"Mauritius":[27],"and":[28,42,45,47,60,75,108],"French-based":[31],"creole":[32],"language.":[33],"MorisienMT":[34],"consists":[35],"parallel":[38,89],"corpus":[39,50],"between":[40],"English":[41],"Morisien,":[43],"French":[44],"Morisien":[46,59,115],"monolingual":[49],"Morisien.":[52],"We":[53,100],"first":[54],"give":[55],"an":[56],"overview":[57],"then":[61],"steps":[64],"taken":[65],"to":[66],"create":[67],"corpora":[69,90,96],"and,":[70],"from":[71],"it,":[72],"training":[74],"evaluation":[76],"splits.":[77],"Thereafter,":[78],"establish":[80],"variety":[82],"baseline":[84],"models":[85],"using":[86],"created":[88],"as":[91,93],"well":[92],"large":[94],"French--English":[95],"transfer":[98],"learning.":[99],"release":[101],"our":[102],"datasets":[103],"publicly":[104],"research":[106,113],"purposes":[107],"hope":[109],"that":[110],"spurs":[112],"translation.":[117]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2022-06-13T00:00:00"}
