{"id":"https://openalex.org/W4221156826","doi":"https://doi.org/10.48550/arxiv.2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","display_name":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","publication_year":2022,"publication_date":"2022-03-24","ids":{"openalex":"https://openalex.org/W4221156826","doi":"https://doi.org/10.48550/arxiv.2203.13357"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2203.13357","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.13357","pdf_url":"https://arxiv.org/pdf/2203.13357","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.13357","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112924039","display_name":"Alham Fikri Aji","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aji, Alham Fikri","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085516032","display_name":"Genta Indra Winata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Winata, Genta Indra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065822589","display_name":"Fajri Koto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koto, Fajri","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084836777","display_name":"Samuel Cahyawijaya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cahyawijaya, Samuel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079062342","display_name":"Ade Romadhony","orcid":"https://orcid.org/0000-0002-2930-1689"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romadhony, Ade","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054993995","display_name":"Rahmad Mahendra","orcid":"https://orcid.org/0000-0003-1107-7073"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahendra, Rahmad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067017155","display_name":"Kemal Kurniawan","orcid":"https://orcid.org/0000-0002-4231-4310"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kurniawan, Kemal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072312522","display_name":"David Moeljadi","orcid":"https://orcid.org/0000-0002-7549-0732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moeljadi, David","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074108268","display_name":"Radityo Eko Prasojo","orcid":"https://orcid.org/0000-0002-5148-7299"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prasojo, Radityo Eko","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103085805","display_name":"Timothy Baldwin","orcid":"https://orcid.org/0000-0002-4445-1386"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baldwin, Timothy","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032767467","display_name":"Jey Han Lau","orcid":"https://orcid.org/0000-0002-1647-4628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lau, Jey Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037310413","display_name":"Sebastian Ruder","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruder, Sebastian","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5112924039"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"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/T10028","display_name":"Topic Modeling","score":0.9872999787330627,"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":0.9872999787330627,"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":0.9613999724388123,"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/indonesian","display_name":"Indonesian","score":0.7321099042892456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.609103262424469},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.546035647392273},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5373917818069458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5206743478775024},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.45361047983169556}],"concepts":[{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.7321099042892456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.609103262424469},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.546035647392273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5373917818069458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5206743478775024},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.45361047983169556},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2203.13357","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.13357","pdf_url":"https://arxiv.org/pdf/2203.13357","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":"doi:10.48550/arxiv.2203.13357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.13357","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":"pmh:oai:arXiv.org:2203.13357","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.13357","pdf_url":"https://arxiv.org/pdf/2203.13357","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4242621793","https://openalex.org/W648807974","https://openalex.org/W4229837155","https://openalex.org/W4236086937","https://openalex.org/W2294302573","https://openalex.org/W4312419881","https://openalex.org/W2086953810","https://openalex.org/W2512763533","https://openalex.org/W4248715694","https://openalex.org/W3204019825"],"abstract_inverted_index":{"NLP":[0,50,61,70,80],"research":[1,51],"is":[2],"impeded":[3],"by":[4,15],"a":[5],"lack":[6],"of":[7,11,38,45,49,68,86],"resources":[8],"and":[9,18,32,62],"awareness":[10],"the":[12,22,27,33,39,46,66],"challenges":[13,58],"presented":[14],"underrepresented":[16,91],"languages":[17,23,85],"dialects.":[19],"Focusing":[20],"on":[21],"spoken":[24],"in":[25,59],"Indonesia,":[26],"second":[28],"most":[29,35],"linguistically":[30],"diverse":[31],"fourth":[34],"populous":[36],"nation":[37],"world,":[40],"we":[41,73],"provide":[42,74],"an":[43],"overview":[44],"current":[47,69],"state":[48],"for":[52,84],"Indonesia's":[53],"700+":[54],"languages.":[55,92],"We":[56],"highlight":[57],"Indonesian":[60],"how":[63],"these":[64],"affect":[65],"performance":[67],"systems.":[71],"Finally,":[72],"general":[75],"recommendations":[76],"to":[77],"help":[78],"develop":[79],"technology":[81],"not":[82],"only":[83],"Indonesia":[87],"but":[88],"also":[89],"other":[90]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
