{"id":"https://openalex.org/W3048530634","doi":"https://doi.org/10.1109/access.2020.3015778","title":"Data Augmentation Methods for Low-Resource Orthographic Syllabification","display_name":"Data Augmentation Methods for Low-Resource Orthographic Syllabification","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3048530634","doi":"https://doi.org/10.1109/access.2020.3015778","mag":"3048530634"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3015778","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3015778","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2020.3015778","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100782869","display_name":"Suyanto Suyanto","orcid":"https://orcid.org/0000-0003-2262-030X"},"institutions":[{"id":"https://openalex.org/I862893732","display_name":"Telkom University","ror":"https://ror.org/0004wsx81","country_code":"ID","type":"education","lineage":["https://openalex.org/I862893732"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Suyanto Suyanto","raw_affiliation_strings":["School of Computing, Telkom University, Bandung, Indonesia"],"raw_orcid":"https://orcid.org/0000-0002-8897-8091","affiliations":[{"raw_affiliation_string":"School of Computing, Telkom University, Bandung, Indonesia","institution_ids":["https://openalex.org/I862893732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057724298","display_name":"Kemas Muslim Lhaksmana","orcid":"https://orcid.org/0000-0002-0223-4658"},"institutions":[{"id":"https://openalex.org/I862893732","display_name":"Telkom University","ror":"https://ror.org/0004wsx81","country_code":"ID","type":"education","lineage":["https://openalex.org/I862893732"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Kemas M. Lhaksmana","raw_affiliation_strings":["School of Computing, Telkom University, Bandung, Indonesia"],"raw_orcid":"https://orcid.org/0000-0002-0223-4658","affiliations":[{"raw_affiliation_string":"School of Computing, Telkom University, Bandung, Indonesia","institution_ids":["https://openalex.org/I862893732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018906358","display_name":"Moch Arif Bijaksana","orcid":"https://orcid.org/0000-0001-9315-7653"},"institutions":[{"id":"https://openalex.org/I862893732","display_name":"Telkom University","ror":"https://ror.org/0004wsx81","country_code":"ID","type":"education","lineage":["https://openalex.org/I862893732"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Moch Arif Bijaksana","raw_affiliation_strings":["School of Computing, Telkom University, Bandung, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Telkom University, Bandung, Indonesia","institution_ids":["https://openalex.org/I862893732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067094321","display_name":"Adriana Kurniawan","orcid":null},"institutions":[{"id":"https://openalex.org/I862893732","display_name":"Telkom University","ror":"https://ror.org/0004wsx81","country_code":"ID","type":"education","lineage":["https://openalex.org/I862893732"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Adriana Kurniawan","raw_affiliation_strings":["School of Computing, Telkom University, Bandung, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Telkom University, Bandung, Indonesia","institution_ids":["https://openalex.org/I862893732"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100782869"],"corresponding_institution_ids":["https://openalex.org/I862893732"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.5436,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73726578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"8","issue":null,"first_page":"147399","last_page":"147406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9933000206947327,"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/T12031","display_name":"Speech and dialogue systems","score":0.9933000206947327,"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":0.9896000027656555,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9883000254631042,"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/bigram","display_name":"Bigram","score":0.9770454168319702},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7903290390968323},{"id":"https://openalex.org/keywords/syllabification","display_name":"Syllabification","score":0.7492725253105164},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6060501933097839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5989533066749573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5879035592079163},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5229557156562805},{"id":"https://openalex.org/keywords/phonotactics","display_name":"Phonotactics","score":0.49978065490722656},{"id":"https://openalex.org/keywords/recall-rate","display_name":"Recall rate","score":0.4445789158344269},{"id":"https://openalex.org/keywords/hangul","display_name":"Hangul","score":0.42282742261886597},{"id":"https://openalex.org/keywords/consonant","display_name":"Consonant","score":0.41750895977020264},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.390083909034729},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34660717844963074},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.13406729698181152}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9770454168319702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7903290390968323},{"id":"https://openalex.org/C2779211743","wikidata":"https://www.wikidata.org/wiki/Q11994045","display_name":"Syllabification","level":3,"score":0.7492725253105164},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6060501933097839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5989533066749573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5879035592079163},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5229557156562805},{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.49978065490722656},{"id":"https://openalex.org/C2987098735","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"Recall rate","level":2,"score":0.4445789158344269},{"id":"https://openalex.org/C554519600","wikidata":"https://www.wikidata.org/wiki/Q8222","display_name":"Hangul","level":2,"score":0.42282742261886597},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.41750895977020264},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.390083909034729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34660717844963074},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.13406729698181152},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.0},{"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":"doi:10.1109/access.2020.3015778","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3015778","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:80cb4ebc0486482b933e902b6bffd04e","is_oa":true,"landing_page_url":"https://doaj.org/article/80cb4ebc0486482b933e902b6bffd04e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 147399-147406 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3015778","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3015778","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W91440482","https://openalex.org/W170339507","https://openalex.org/W182267589","https://openalex.org/W203446784","https://openalex.org/W1586887050","https://openalex.org/W1953462931","https://openalex.org/W1997076137","https://openalex.org/W2109664771","https://openalex.org/W2110442145","https://openalex.org/W2114705006","https://openalex.org/W2115817433","https://openalex.org/W2136978972","https://openalex.org/W2167623656","https://openalex.org/W2174337630","https://openalex.org/W2187325801","https://openalex.org/W2213913141","https://openalex.org/W2251899728","https://openalex.org/W2547253535","https://openalex.org/W2575363158","https://openalex.org/W2770371702","https://openalex.org/W2792441356","https://openalex.org/W2794041065","https://openalex.org/W2820665278","https://openalex.org/W2888864950","https://openalex.org/W2898766142","https://openalex.org/W2899816737","https://openalex.org/W2900225066","https://openalex.org/W2902964203","https://openalex.org/W2904833599","https://openalex.org/W2907622093","https://openalex.org/W2911738025","https://openalex.org/W2914066281","https://openalex.org/W2914650326","https://openalex.org/W2918532652","https://openalex.org/W2938186624","https://openalex.org/W2944762197","https://openalex.org/W2946595319","https://openalex.org/W2963537482","https://openalex.org/W2969145661","https://openalex.org/W2971041032","https://openalex.org/W2979331487","https://openalex.org/W3000816625","https://openalex.org/W3007367295","https://openalex.org/W3105490285","https://openalex.org/W4243383543","https://openalex.org/W4300427683","https://openalex.org/W6603644044","https://openalex.org/W6606959416","https://openalex.org/W6607389590","https://openalex.org/W6676373471","https://openalex.org/W6686921764","https://openalex.org/W6691899163","https://openalex.org/W6732421952","https://openalex.org/W6741459021","https://openalex.org/W6745265922","https://openalex.org/W6756116795","https://openalex.org/W6815512688"],"related_works":["https://openalex.org/W1518493474","https://openalex.org/W3030063679","https://openalex.org/W2102951823","https://openalex.org/W2899816737","https://openalex.org/W2547253535","https://openalex.org/W2151852520","https://openalex.org/W1589286968","https://openalex.org/W642320556","https://openalex.org/W4743243","https://openalex.org/W2592134930"],"abstract_inverted_index":{"An":[0,51,150],"n-gram":[1],"syllabification":[2,144],"model":[3,186,193],"generally":[4],"produces":[5],"a":[6,11,29,111,122,217,237],"high":[7,20],"error":[8,94],"rate":[9,21,95],"for":[10,161],"low-resource":[12],"language,":[13],"such":[14],"as":[15],"Indonesian,":[16],"because":[17],"of":[18,22,31,34,61,70,78,114,142,172,219],"the":[19,41,59,68,86,92,102,140,147,169,173,178,183,197,210],"out-of-vocabulary":[23],"(OOV)":[24],"n-grams.":[25],"In":[26,119],"this":[27,120],"paper,":[28],"combination":[30,60,171,218],"three":[32,62,174],"methods":[33,65],"data":[35,63],"augmentations":[36],"is":[37,128,194,207,214],"proposed":[38,129,170,192],"to":[39,84,99,109,117,138,189,196],"solve":[40],"problem,":[42],"namely":[43],"swapping":[44,104,136],"consonant-graphemes,":[45],"flipping":[46,79,134],"onsets,":[47],"and":[48,73,130,135,229],"transposing":[49,124],"nuclei.":[50],"investigation":[52],"on":[53,153],"50k":[54],"Indonesian":[55,164],"words":[56,166],"shows":[57],"that":[58,168],"augmentation":[64,126],"drastically":[66],"increases":[67],"amount":[69],"both":[71,133],"unigrams":[72],"bigrams.":[74,149],"A":[75],"previous":[76,103],"procedure":[77],"onsets":[80],"has":[81,106],"been":[82,107],"proven":[83,108],"enhance":[85],"standard":[87,184],"bigram-syllabification":[88],"by":[89,97,182,187],"relatively":[90,176],"decreasing":[91],"syllable":[93],"(SER)":[96],"up":[98,116,188],"18.02%.":[100],"Meanwhile,":[101],"consonant-graphemes":[105],"give":[110],"relative":[112],"decrement":[113],"SER":[115,180],"31.39%.":[118],"research,":[121],"new":[123],"nuclei-based":[125],"method":[127],"combined":[131],"with":[132],"procedures":[137,175],"tackle":[139],"drawback":[141],"bigram":[143,185],"in":[145,201],"handling":[146],"OOV":[148],"evaluation":[151],"based":[152],"k-fold":[154],"cross-validation":[155],"(k-FCV),":[156],"using":[157,216],"k":[158],"=":[159],"5,":[160],"50":[162],"thousand":[163],"formal":[165],"concludes":[167],"decreases":[177],"mean":[179],"produced":[181],"37.63%.":[190],"The":[191],"comparable":[195],"fuzzy":[198],"k-nearest":[199],"neighbor":[200],"every":[202],"class":[203],"(FkNNC)-based":[204],"model.":[205],"It":[206],"worse":[208],"than":[209],"state-of-the-art":[211],"model,":[212],"which":[213],"developed":[215],"bidirectional":[220],"long":[221],"short-term":[222],"memory":[223],"(BiLSTM),":[224],"convolutional":[225],"neural":[226],"networks":[227],"(CNN),":[228],"conditional":[230],"random":[231],"fields":[232],"(CRF),":[233],"but":[234],"it":[235],"offers":[236],"low":[238],"complexity.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}