{"id":"https://openalex.org/W7126433952","doi":"https://doi.org/10.18653/v1/2022.wmt-1.98","title":"Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages","display_name":"Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W7126433952","doi":"https://doi.org/10.18653/v1/2022.wmt-1.98"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2022.wmt-1.98","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wmt-1.98","pdf_url":"https://aclanthology.org/2022.wmt-1.98.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 Seventh Conference on Machine Translation (WMT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2022.wmt-1.98.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124557134","display_name":"Idris Abdulmumin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Idris Abdulmumin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091348511","display_name":"Michael Beukman","orcid":"https://orcid.org/0000-0002-5468-284X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Beukman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124500325","display_name":"Jesujoba O. Alabi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jesujoba O. Alabi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124555012","display_name":"Chris Emezue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Emezue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067215283","display_name":"Everlyn Asiko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Everlyn Asiko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091302921","display_name":"Tosin Adewumi","orcid":"https://orcid.org/0000-0002-5582-2031"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tosin Adewumi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124628213","display_name":"Shamsuddeen Hassan Muhammad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shamsuddeen Hassan Muhammad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076302977","display_name":"Mofetoluwa Adeyemi","orcid":"https://orcid.org/0009-0003-2859-7136"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mofetoluwa Adeyemi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043203940","display_name":"Oreen Yousuf","orcid":"https://orcid.org/0009-0000-3320-813X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oreen Yousuf","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102841588","display_name":"Sahib Singh","orcid":"https://orcid.org/0000-0002-6328-8203"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sahib Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124576661","display_name":"Tajuddeen Rabiu Gwadabe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tajuddeen Rabiu Gwadabe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48083871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1001","last_page":"1014"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2232999950647354,"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":0.2232999950647354,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.02889999933540821,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.017799999564886093,"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/translation","display_name":"Translation (biology)","score":0.4927999973297119},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.46480000019073486},{"id":"https://openalex.org/keywords/languages-of-africa","display_name":"Languages of Africa","score":0.3253999948501587},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.2766999900341034},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2660999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6164000034332275},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5400999784469604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5325999855995178},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4927999973297119},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.42160001397132874},{"id":"https://openalex.org/C108494575","wikidata":"https://www.wikidata.org/wiki/Q207930","display_name":"Languages of Africa","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.wmt-1.98","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wmt-1.98","pdf_url":"https://aclanthology.org/2022.wmt-1.98.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 Seventh Conference on Machine Translation (WMT)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.wmt-1.98","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wmt-1.98","pdf_url":"https://aclanthology.org/2022.wmt-1.98.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 Seventh Conference on Machine Translation (WMT)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7450125813484192}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337380","display_name":"Division of Mathematical Sciences","ror":"https://ror.org/051fftw81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126433952.pdf","grobid_xml":"https://content.openalex.org/works/W7126433952.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Idris":[0],"Abdulmumin,":[1],"Michael":[2],"Beukman,":[3],"Jesujoba":[4],"O.":[5],"Alabi,":[6],"Chris":[7],"Emezue,":[8],"Everlyn":[9],"Asiko,":[10],"Tosin":[11],"Adewumi,":[12],"Shamsuddeen":[13],"Hassan":[14],"Muhammad,":[15],"Mofetoluwa":[16],"Adeyemi,":[17],"Oreen":[18],"Yousuf,":[19],"Sahib":[20],"Singh,":[21],"Tajuddeen":[22],"Rabiu":[23],"Gwadabe.":[24],"Proceedings":[25],"of":[26],"the":[27],"Seventh":[28],"Conference":[29],"on":[30],"Machine":[31],"Translation":[32],"(WMT).":[33],"2022.":[34]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}
