{"id":"https://openalex.org/W4402671569","doi":"https://doi.org/10.18653/v1/2024.acl-long.620","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","display_name":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402671569","doi":"https://doi.org/10.18653/v1/2024.acl-long.620"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.acl-long.620","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-long.620","pdf_url":"https://aclanthology.org/2024.acl-long.620.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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.acl-long.620.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050856399","display_name":"Shivalika Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shivalika Singh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011552000","display_name":"Freddie Vargus","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Freddie Vargus","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036836679","display_name":"Daniel D\u2019souza","orcid":"https://orcid.org/0000-0001-7843-8596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel D\u2019souza","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015011965","display_name":"B\u00f6rje F. Karlsson","orcid":"https://orcid.org/0000-0001-8925-360X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B\u00f6rje Karlsson","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022712053","display_name":"Abinaya Mahendiran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abinaya Mahendiran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068810050","display_name":"Wei-Yin Ko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Yin Ko","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090912879","display_name":"Herumb Shandilya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herumb Shandilya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086603416","display_name":"Jay Patel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jay Patel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093917425","display_name":"Deividas Mataciunas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deividas Mataciunas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093917420","display_name":"Laura O'Mahony","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laura O\u2019Mahony","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025357679","display_name":"Mike Zhang","orcid":"https://orcid.org/0000-0003-1218-5201"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]},{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mike Zhang","raw_affiliation_strings":["IT University of Copenhagen, DK","Aalborg University, The Technical Faculty of IT and Design, DK"],"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, DK","institution_ids":["https://openalex.org/I83467386"]},{"raw_affiliation_string":"Aalborg University, The Technical Faculty of IT and Design, DK","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085677889","display_name":"Ramith Hettiarachchi","orcid":"https://orcid.org/0000-0001-7070-8213"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramith Hettiarachchi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025757578","display_name":"Joseph B. Wilson","orcid":"https://orcid.org/0000-0002-3831-9725"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph Wilson","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051287569","display_name":"Marina Machado","orcid":"https://orcid.org/0000-0001-7718-5021"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marina Machado","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104242935","display_name":"Luisa Souza Moura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luisa Moura","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066939448","display_name":"Dominik Krzemi\u0144ski","orcid":"https://orcid.org/0000-0003-4568-0583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dominik Krzemi\u0144ski","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012789622","display_name":"Hakimeh Fadaei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hakimeh Fadaei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093917421","display_name":"Irem Erg\u00fcn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irem Ergun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093917422","display_name":"Ifeoma Okoh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ifeoma Okoh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093917423","display_name":"Aisha Alaagib","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aisha Alaagib","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024173490","display_name":"Oshan Mudannayake","orcid":"https://orcid.org/0000-0002-9598-457X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oshan Mudannayake","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082096652","display_name":"Zaid Alyafeai","orcid":"https://orcid.org/0009-0003-1774-5236"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zaid Alyafeai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079915395","display_name":"Vu Minh Chien","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vu Chien","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037310413","display_name":"Sebastian Ruder","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Ruder","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093917424","display_name":"Surya Guthikonda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Surya Guthikonda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082020464","display_name":"Emad A. Alghamdi","orcid":"https://orcid.org/0000-0002-2316-3457"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emad Alghamdi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026789962","display_name":"Sebastian Gehrmann","orcid":"https://orcid.org/0000-0002-8257-9516"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Gehrmann","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000043237","display_name":"Niklas Muennighoff","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niklas Muennighoff","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018864006","display_name":"Max Bartolo","orcid":"https://orcid.org/0009-0007-3301-7895"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Max Bartolo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048307591","display_name":"Julia Kreutzer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julia Kreutzer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063061204","display_name":"Ahmet \u00dcst\u00fcn","orcid":"https://orcid.org/0000-0002-1640-4291"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmet \u00dcst\u00fcn","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070153551","display_name":"Marzieh Fadaee","orcid":"https://orcid.org/0000-0002-4447-1213"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marzieh Fadaee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078850040","display_name":"Sara Hooker","orcid":"https://orcid.org/0000-0002-0190-6459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sara Hooker","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":33,"corresponding_author_ids":["https://openalex.org/A5050856399"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.7026,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.98137639,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11521","last_page":"11567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.843500018119812,"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":0.843500018119812,"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/computer-science","display_name":"Computer science","score":0.7227116823196411},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.5020961761474609},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4158618152141571},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05116534233093262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7227116823196411},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.5020961761474609},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4158618152141571},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05116534233093262},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.acl-long.620","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-long.620","pdf_url":"https://aclanthology.org/2024.acl-long.620.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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.acl-long.620","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-long.620","pdf_url":"https://aclanthology.org/2024.acl-long.620.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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402671569.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Shivalika":[0],"Singh,":[1],"Freddie":[2],"Vargus,":[3],"Daniel":[4],"D\u2019souza,":[5],"B\u00f6rje":[6],"F.":[7],"Karlsson,":[8],"Abinaya":[9],"Mahendiran,":[10],"Wei-Yin":[11],"Ko,":[12],"Herumb":[13],"Shandilya,":[14],"Jay":[15],"Patel,":[16],"Deividas":[17],"Mataciunas,":[18],"Laura":[19],"O\u2019Mahony,":[20],"Mike":[21],"Zhang,":[22],"Ramith":[23],"Hettiarachchi,":[24],"Joseph":[25],"Wilson,":[26],"Marina":[27],"Machado,":[28],"Luisa":[29],"Moura,":[30],"Dominik":[31],"Krzemi\u0144ski,":[32],"Hakimeh":[33],"Fadaei,":[34],"Irem":[35],"Ergun,":[36],"Ifeoma":[37],"Okoh,":[38],"Aisha":[39],"Alaagib,":[40],"Oshan":[41],"Mudannayake,":[42],"Zaid":[43],"Alyafeai,":[44],"Vu":[45],"Chien,":[46],"Sebastian":[47,53],"Ruder,":[48],"Surya":[49],"Guthikonda,":[50],"Emad":[51],"Alghamdi,":[52],"Gehrmann,":[54],"Niklas":[55],"Muennighoff,":[56],"Max":[57],"Bartolo,":[58],"Julia":[59],"Kreutzer,":[60],"Ahmet":[61],"\u00dcst\u00fcn,":[62],"Marzieh":[63],"Fadaee,":[64],"Sara":[65],"Hooker.":[66],"Proceedings":[67],"of":[68,73],"the":[69,74],"62nd":[70],"Annual":[71],"Meeting":[72],"Association":[75],"for":[76],"Computational":[77],"Linguistics":[78],"(Volume":[79],"1:":[80],"Long":[81],"Papers).":[82],"2024.":[83]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":4}],"updated_date":"2026-01-21T23:30:37.877113","created_date":"2025-10-10T00:00:00"}
