{"id":"https://openalex.org/W4366274332","doi":"https://doi.org/10.1145/3592854","title":"Dataset Enhancement and Multilingual Transfer for Named Entity Recognition in the Indonesian Language","display_name":"Dataset Enhancement and Multilingual Transfer for Named Entity Recognition in the Indonesian Language","publication_year":2023,"publication_date":"2023-04-18","ids":{"openalex":"https://openalex.org/W4366274332","doi":"https://doi.org/10.1145/3592854"},"language":"en","primary_location":{"id":"doi:10.1145/3592854","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3592854","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3592854","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3592854","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001596108","display_name":"Siti Oryza Khairunnisa","orcid":"https://orcid.org/0000-0002-5917-6006"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Siti Oryza Khairunnisa","raw_affiliation_strings":["Tokyo Metropolitan University, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5917-6006","affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069277248","display_name":"Zhousi Chen","orcid":"https://orcid.org/0000-0002-6341-8338"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhousi Chen","raw_affiliation_strings":["Tokyo Metropolitan University, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6341-8338","affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061931124","display_name":"Mamoru Komachi","orcid":"https://orcid.org/0000-0003-1166-1739"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mamoru Komachi","raw_affiliation_strings":["Tokyo Metropolitan University, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1166-1739","affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":1.8134,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.87114299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"22","issue":"6","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9904000163078308,"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":0.8618184924125671},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6789976358413696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6157787442207336},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6122360825538635},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5890664458274841},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5658890008926392},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5417987704277039},{"id":"https://openalex.org/keywords/contextualization","display_name":"Contextualization","score":0.5352521538734436},{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.5105332136154175},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5099719762802124},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.49206942319869995},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43113410472869873},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.4235053062438965},{"id":"https://openalex.org/keywords/multilingualism","display_name":"Multilingualism","score":0.4227759838104248},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2146485149860382}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8618184924125671},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6789976358413696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6157787442207336},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6122360825538635},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5890664458274841},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5658890008926392},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5417987704277039},{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.5352521538734436},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.5105332136154175},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5099719762802124},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.49206942319869995},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43113410472869873},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.4235053062438965},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.4227759838104248},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2146485149860382},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3592854","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3592854","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3592854","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3592854","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3592854","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3592854","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366274332.pdf","grobid_xml":"https://content.openalex.org/works/W4366274332.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W567338163","https://openalex.org/W1522301498","https://openalex.org/W1524281572","https://openalex.org/W1631063262","https://openalex.org/W1975879668","https://openalex.org/W2007315962","https://openalex.org/W2109593304","https://openalex.org/W2141766660","https://openalex.org/W2144578941","https://openalex.org/W2148249305","https://openalex.org/W2296283641","https://openalex.org/W2493916176","https://openalex.org/W2514249165","https://openalex.org/W2538358357","https://openalex.org/W2543306797","https://openalex.org/W2574330554","https://openalex.org/W2611838487","https://openalex.org/W2757931423","https://openalex.org/W2889191148","https://openalex.org/W2889383784","https://openalex.org/W2933138175","https://openalex.org/W2952638691","https://openalex.org/W2963341956","https://openalex.org/W2963979492","https://openalex.org/W2964114970","https://openalex.org/W2970849641","https://openalex.org/W2970854433","https://openalex.org/W2978339802","https://openalex.org/W2988692181","https://openalex.org/W2997518171","https://openalex.org/W3034708897","https://openalex.org/W3035390927","https://openalex.org/W3037109418","https://openalex.org/W3098744621","https://openalex.org/W3104415840","https://openalex.org/W3114463723","https://openalex.org/W3116295307","https://openalex.org/W3165977309","https://openalex.org/W3177049011","https://openalex.org/W4205918858","https://openalex.org/W4233907442","https://openalex.org/W4237040408","https://openalex.org/W4256000987","https://openalex.org/W4404783704","https://openalex.org/W4404783772"],"related_works":["https://openalex.org/W4250494529","https://openalex.org/W1964783010","https://openalex.org/W2399696375","https://openalex.org/W45206245","https://openalex.org/W2211396092","https://openalex.org/W2061834489","https://openalex.org/W3088215229","https://openalex.org/W2078793151","https://openalex.org/W3047727388","https://openalex.org/W2759598007"],"abstract_inverted_index":{"Named":[0],"entity":[1],"recognition":[2],"in":[3,10,119,133,160],"the":[4,34,42,69,97,101,107,114,144,148,161],"Indonesian":[5,150],"language":[6,87,102,151],"has":[7],"significantly":[8],"developed":[9],"recent":[11],"years.":[12],"However,":[13],"it":[14],"still":[15],"lacks":[16],"standardized":[17],"publicly":[18],"available":[19,25,71],"corpora;":[20],"a":[21,157],"small":[22],"dataset":[23,35],"is":[24,110],"but":[26],"suffers":[27],"from":[28,51,100],"inconsistent":[29],"annotations.":[30],"Therefore,":[31],"we":[32,73,104],"re-annotated":[33],"to":[36,47,96,129,166,170],"improve":[37],"its":[38],"consistency":[39],"and":[40,62,77,84,92,141,152],"benefit":[41],"community.":[43],"Our":[44],"re-annotation":[45],"led":[46],"better":[48,75],"training":[49],"results":[50],"an":[52],"effective":[53],"baseline":[54],"model":[55,109],"consisting":[56],"of":[57],"bidirectional":[58],"long":[59],"short-term":[60],"memory":[61],"conditional":[63],"random":[64],"fields.":[65],"To":[66],"fully":[67],"utilize":[68,130],"limited":[70],"data,":[72],"utilized":[74],"contextualization":[76],"transferred":[78],"external":[79],"knowledge":[80],"by":[81],"exploiting":[82],"monolingual":[83,108],"multilingual":[85,115],"pre-trained":[86],"models,":[88,103],"such":[89],"as":[90,143],"IndoBERT":[91],"XLM-RoBERTa.":[93],"In":[94],"addition":[95],"general":[98],"improvement":[99],"observed":[105],"that":[106,154],"more":[111],"sensitive,":[112],"while":[113],"ones":[116],"show":[117],"advantages":[118],"rich":[120],"morphological":[121,167],"knowledge.":[122],"We":[123,136],"also":[124],"applied":[125],"cross-lingual":[126],"transfer":[127,163],"learning":[128],"high-resource":[131],"corpora":[132],"other":[134],"languages.":[135],"adopted":[137],"English,":[138],"Spanish,":[139],"Dutch,":[140],"German":[142],"source":[145],"languages":[146],"for":[147],"target":[149],"found":[153],"Dutch":[155],"plays":[156],"special":[158],"role":[159],"data":[162],"method":[164],"due":[165],"similarity":[168],"attributable":[169],"historical":[171],"reasons.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}