{"id":"https://openalex.org/W7204481077","doi":"https://doi.org/10.5281/zenodo.22121083","title":"Indonesian\u2013Sekar (Papua Kokas) Parallel Corpus \u2014 Public Sample of 500 Sentence Pairs","display_name":"Indonesian\u2013Sekar (Papua Kokas) Parallel Corpus \u2014 Public Sample of 500 Sentence Pairs","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204481077","doi":"https://doi.org/10.5281/zenodo.22121083"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22121083","doi":"https://doi.org/10.5281/zenodo.22121083","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22121083","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22121083","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084580561","display_name":"Nira Radita","orcid":"https://orcid.org/0000-0003-1643-4252","observed_orcids":["https://orcid.org/0000-0003-1643-4252"]},"institutions":[{"id":"https://openalex.org/I4405275169","display_name":"Universitas Bhinneka Nusantara","ror":"https://ror.org/032sex452","country_code":"ID","type":"education","lineage":["https://openalex.org/I4405275169"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Radita, Nira","raw_affiliation_strings":["Universitas Bhinneka Nusantara"],"raw_orcid":"https://orcid.org/0000-0003-1643-4252","affiliations":[{"raw_affiliation_string":"Universitas Bhinneka Nusantara","institution_ids":["https://openalex.org/I4405275169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086456256","display_name":"Mukhlis Amien","orcid":"https://orcid.org/0000-0002-1848-167X","observed_orcids":["https://orcid.org/0000-0002-1848-167X"]},"institutions":[{"id":"https://openalex.org/I4405275169","display_name":"Universitas Bhinneka Nusantara","ror":"https://ror.org/032sex452","country_code":"ID","type":"education","lineage":["https://openalex.org/I4405275169"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Amien, Mukhlis","raw_affiliation_strings":["Universitas Bhinneka Nusantara"],"raw_orcid":"https://orcid.org/0000-0002-1848-167X","affiliations":[{"raw_affiliation_string":"Universitas Bhinneka Nusantara","institution_ids":["https://openalex.org/I4405275169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148457300","display_name":"Ronggo Haikal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405275169","display_name":"Universitas Bhinneka Nusantara","ror":"https://ror.org/032sex452","country_code":"ID","type":"education","lineage":["https://openalex.org/I4405275169"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Haikal, Ronggo","raw_affiliation_strings":["Universitas Bhinneka Nusantara"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitas Bhinneka Nusantara","institution_ids":["https://openalex.org/I4405275169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405275169"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.9868000149726868,"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":0.9868000149726868,"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/T10759","display_name":"Translation Studies and Practices","score":0.00279999990016222,"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"}},{"id":"https://openalex.org/T12353","display_name":"Lexicography and Language Studies","score":0.0017000000225380063,"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/endangered-languages","display_name":"endangered languages","score":0.8169999718666077},{"id":"https://openalex.org/keywords/austronesian-languages","display_name":"Austronesian languages","score":0.7870000004768372},{"id":"https://openalex.org/keywords/neural-machine-translation","display_name":"neural machine translation","score":0.800000011920929},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.7559999823570251},{"id":"https://openalex.org/keywords/heritage-speakers","display_name":"heritage speakers","score":0.7429999709129333},{"id":"https://openalex.org/keywords/indigenous-data-governance","display_name":"Indigenous data governance","score":0.8659999966621399},{"id":"https://openalex.org/keywords/care-principles","display_name":"CARE principles","score":0.746999979019165},{"id":"https://openalex.org/keywords/fakfak-regency","display_name":"Fakfak Regency","score":0.7379999756813049}],"concepts":[{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.6741999983787537},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6535000205039978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6025999784469604},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5778999924659729},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5593000054359436},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5479000210762024},{"id":"https://openalex.org/C55958113","wikidata":"https://www.wikidata.org/wiki/Q169480","display_name":"Indigenous","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C2781370049","wikidata":"https://www.wikidata.org/wiki/Q645304","display_name":"Indigenous language","level":3,"score":0.3366999924182892},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3059999942779541},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C140688305","wikidata":"https://www.wikidata.org/wiki/Q5885","display_name":"Tamil","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26510000228881836},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2776725116","wikidata":"https://www.wikidata.org/wiki/Q236935","display_name":"British National Corpus","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22121083","doi":"https://doi.org/10.5281/zenodo.22121083","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22121083","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.22121084","doi":"https://doi.org/10.5281/zenodo.22121084","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22121084","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22121083","doi":"https://doi.org/10.5281/zenodo.22121083","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22121083","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"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/W6906514907","https://openalex.org/W2918449741","https://openalex.org/W7162785619","https://openalex.org/W170711724","https://openalex.org/W3000965575","https://openalex.org/W6906583649","https://openalex.org/W7210265370","https://openalex.org/W7210270317","https://openalex.org/W7115359904","https://openalex.org/W6983601249"],"abstract_inverted_index":{"Public":[0],"sample":[1,122],"of":[2,10,37,47,77,135,163],"500":[3,98],"sentence":[4,14],"pairs":[5,15,99,150],"from":[6,81,105],"a":[7,61,74,168],"parallel":[8],"corpus":[9,54,107,137,148],"4,056":[11],"unique":[12],"Indonesian\u2013Sekar":[13],"built":[16],"to":[17,159],"support":[18],"neural":[19],"machine":[20],"translation":[21],"for":[22,94,142,182],"the":[23,38,44,78,106,111,131,136,139,160,164,173,178],"endangered":[24],"Papua":[25],"Kokas":[26,45,82],"language":[27,36],"(Sekar;":[28],"ISO":[29],"639-3:":[30],"skz;":[31],"Glottolog:":[32],"seka1247),":[33],"an":[34],"Austronesian":[35],"North":[39],"Bomberai":[40],"subgroup":[41],"spoken":[42],"in":[43],"District":[46,83],"Fakfak":[48],"Regency,":[49],"West":[50],"Papua,":[51],"Indonesia.":[52],"The":[53,97,146],"was":[55],"constructed":[56],"through":[57,84],"remote":[58],"elicitation":[59],"with":[60,90,151],"heritage-community":[62],"speaker:":[63],"thematically":[64],"composed":[65],"Indonesian":[66],"stimulus":[67],"sentences":[68],"were":[69,100],"translated":[70],"into":[71],"Sekar":[72],"by":[73],"native":[75],"speaker":[76,174],"older":[79],"generation":[80],"iterative":[85],"WhatsApp":[86],"correspondence":[87],"during":[88],"2024,":[89],"verbal":[91],"informed":[92],"consent":[93],"research":[95],"use.":[96],"sampled":[101],"uniformly":[102],"at":[103],"random":[104],"training":[108],"split":[109],"only;":[110],"held-out":[112],"validation":[113],"and":[114,187],"test":[115],"splits":[116],"are":[117],"not":[118],"included,":[119],"so":[120],"this":[121],"can":[123],"be":[124],"used":[125],"without":[126],"contaminating":[127],"future":[128],"evaluation":[129],"on":[130,156],"full":[132,147],"corpus.":[133],"Governance":[134],"follows":[138],"CARE":[140],"Principles":[141],"Indigenous":[143],"Data":[144],"Governance.":[145],"(4,056":[149],"train/validation/test":[152],"splits)":[153],"is":[154],"available":[155],"reasonable":[157],"request":[158],"corresponding":[161],"author":[162],"associated":[165],"paper,":[166],"under":[167],"data-use":[169],"agreement":[170],"that":[171],"respects":[172],"community's":[175],"authority":[176],"over":[177],"resource.":[179],"See":[180],"README.md":[181],"collection":[183],"methodology,":[184],"format,":[185],"citation,":[186],"contact.":[188]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-28T00:00:00"}