{"id":"https://openalex.org/W4403721875","doi":"https://doi.org/10.1109/access.2024.3486188","title":"Evaluating Neural Network Models for Word Segmentation in Agglutinative Languages: Comparison With Rule-Based Approaches and Statistical Models","display_name":"Evaluating Neural Network Models for Word Segmentation in Agglutinative Languages: Comparison With Rule-Based Approaches and Statistical Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403721875","doi":"https://doi.org/10.1109/access.2024.3486188"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3486188","doi":"https://doi.org/10.1109/access.2024.3486188","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3486188","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,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3486188","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033572800","display_name":"William Eduardo Villegas-Ch","orcid":"https://orcid.org/0000-0002-5421-7710","observed_orcids":["https://orcid.org/0000-0002-5421-7710"]},"institutions":[{"id":"https://openalex.org/I4210102282","display_name":"Universidad de Las Am\u00e9ricas","ror":"https://ror.org/0198j4566","country_code":"EC","type":"education","lineage":["https://openalex.org/I4210102282"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"William Villegas-Ch","raw_affiliation_strings":["Escuela de Ingenier\u00eda en Ciberseguridad, FICA, Universidad de Las Am\u00e9ricas, Quito, Ecuador"],"raw_orcid":"https://orcid.org/0000-0002-5421-7710","affiliations":[{"raw_affiliation_string":"Escuela de Ingenier\u00eda en Ciberseguridad, FICA, Universidad de Las Am\u00e9ricas, Quito, Ecuador","institution_ids":["https://openalex.org/I4210102282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106113696","display_name":"Rommel Gutierrez","orcid":"https://orcid.org/0009-0004-3230-4129","observed_orcids":["https://orcid.org/0009-0004-3230-4129","https://orcid.org/0009-0001-1746-8967"]},"institutions":[{"id":"https://openalex.org/I4210102282","display_name":"Universidad de Las Am\u00e9ricas","ror":"https://ror.org/0198j4566","country_code":"EC","type":"education","lineage":["https://openalex.org/I4210102282"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Rommel Gutierrez","raw_affiliation_strings":["Escuela de Ingenier\u00eda en Ciberseguridad, FICA, Universidad de Las Am\u00e9ricas, Quito, Ecuador"],"raw_orcid":"https://orcid.org/0009-0004-3230-4129","affiliations":[{"raw_affiliation_string":"Escuela de Ingenier\u00eda en Ciberseguridad, FICA, Universidad de Las Am\u00e9ricas, Quito, Ecuador","institution_ids":["https://openalex.org/I4210102282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114229487","display_name":"Alexandra Maldonado Navarro","orcid":"https://orcid.org/0009-0009-5885-5240","observed_orcids":["https://orcid.org/0009-0009-5885-5240"]},"institutions":[{"id":"https://openalex.org/I4210102282","display_name":"Universidad de Las Am\u00e9ricas","ror":"https://ror.org/0198j4566","country_code":"EC","type":"education","lineage":["https://openalex.org/I4210102282"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Alexandra Maldonado Navarro","raw_affiliation_strings":["Escuela de Posgrados, Maestr\u00eda en Derecho Digital, Universidad de Las Am\u00e9ricas, Quito, Ecuador"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Escuela de Posgrados, Maestr\u00eda en Derecho Digital, Universidad de Las Am\u00e9ricas, Quito, Ecuador","institution_ids":["https://openalex.org/I4210102282"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004862157","display_name":"Aracely Mera-Navarrete","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210140740","display_name":"Universidad Internacional del Ecuador","ror":"https://ror.org/04xf2rc74","country_code":"EC","type":"education","lineage":["https://openalex.org/I4210140740"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Aracely Mera-Navarrete","raw_affiliation_strings":["Departamento de Sistemas, Universidad Internacional del Ecuador, Quito, Ecuador"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Sistemas, Universidad Internacional del Ecuador, Quito, Ecuador","institution_ids":["https://openalex.org/I4210140740"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1995,"currency":"USD","value_usd":1995},"apc_paid":{"value":1995,"currency":"USD","value_usd":1995},"fwci":0.3165,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52521991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"12","issue":null,"first_page":"157556","last_page":"157573"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9564999938011169,"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":0.9564999938011169,"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/T10028","display_name":"Topic Modeling","score":0.039799999445676804,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/word-segmentation","display_name":"word segmentation","score":0.9980000257492065},{"id":"https://openalex.org/keywords/agglutinative-languages","display_name":"agglutinative languages","score":0.9990000128746033},{"id":"https://openalex.org/keywords/neural-network-model","display_name":"neural network model","score":0.7319999933242798},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.7559999823570251},{"id":"https://openalex.org/keywords/rule-based-segmentation","display_name":"rule-based segmentation","score":0.7129999995231628},{"id":"https://openalex.org/keywords/turkish-language","display_name":"Turkish language","score":0.7350000143051147},{"id":"https://openalex.org/keywords/finnish","display_name":"Finnish language","score":0.9990000128746033},{"id":"https://openalex.org/keywords/hungarian-language","display_name":"Hungarian language","score":0.9909999966621399},{"id":"https://openalex.org/keywords/nahuatl","display_name":"Nahuatl language","score":0.9990000128746033},{"id":"https://openalex.org/keywords/swahili-language","display_name":"Swahili language","score":0.9990000128746033},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.8220000267028809},{"id":"https://openalex.org/keywords/morphological-complexity","display_name":"morphological complexity","score":0.6899999976158142}],"concepts":[{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.9007646441459656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8070341348648071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6137726902961731},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5523748993873596},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5346725583076477},{"id":"https://openalex.org/C149271511","wikidata":"https://www.wikidata.org/wiki/Q1417149","display_name":"Rule-based system","level":2,"score":0.46946871280670166},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45753008127212524},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35864564776420593},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.1564086675643921},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10373532772064209},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3486188","doi":"https://doi.org/10.1109/access.2024.3486188","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3486188","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,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:56cbda6b8d1e40c580583703dde03290","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/56cbda6b8d1e40c580583703dde03290","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"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 12, Pp 157556-157573 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3486188","doi":"https://doi.org/10.1109/access.2024.3486188","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3486188","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,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2052847729","https://openalex.org/W2062289558","https://openalex.org/W2160947557","https://openalex.org/W2797790703","https://openalex.org/W3001479960","https://openalex.org/W3011441868","https://openalex.org/W3033400291","https://openalex.org/W3159115358","https://openalex.org/W3182319652","https://openalex.org/W3199024477","https://openalex.org/W3202499226","https://openalex.org/W3217233014","https://openalex.org/W4224439062","https://openalex.org/W4281756552","https://openalex.org/W4285197036","https://openalex.org/W4293732343","https://openalex.org/W4295681711","https://openalex.org/W4297491180","https://openalex.org/W4316805162","https://openalex.org/W4320069614","https://openalex.org/W4323320277","https://openalex.org/W4324393920","https://openalex.org/W4327599708","https://openalex.org/W4327737695","https://openalex.org/W4327941905","https://openalex.org/W4379057296","https://openalex.org/W4381383723","https://openalex.org/W4381488486","https://openalex.org/W4385303989","https://openalex.org/W4385451462","https://openalex.org/W4385639677","https://openalex.org/W4386295648","https://openalex.org/W4388121508","https://openalex.org/W4389223002","https://openalex.org/W4389744045","https://openalex.org/W4390362897","https://openalex.org/W4390945568","https://openalex.org/W4391103530","https://openalex.org/W4391426158","https://openalex.org/W4391621166","https://openalex.org/W4392251487","https://openalex.org/W4392308284","https://openalex.org/W4392908041"],"related_works":["https://openalex.org/W2998280981","https://openalex.org/W3086096110","https://openalex.org/W4413405754","https://openalex.org/W7166504253","https://openalex.org/W3009096638","https://openalex.org/W2962885853","https://openalex.org/W7203794009","https://openalex.org/W2804859241","https://openalex.org/W4378651546","https://openalex.org/W2514307064"],"abstract_inverted_index":{"Word":[0],"segmentation":[1,169],"in":[2,27,47,121,137,167,178,182],"agglutinative":[3,57],"languages":[4,58],"presents":[5],"significant":[6],"challenges":[7],"due":[8],"to":[9,49,74,124],"morphological":[10],"complexity":[11],"and":[12,21,45,65,71,78,83,99,118,126,146,170],"variability":[13],"of":[14,36,155,163],"linguistic":[15,184],"structure.":[16],"Although":[17],"practical,":[18],"traditional":[19,51,141],"rule-based":[20,98,110],"statistical":[22,100],"model-based":[23,101],"approaches":[24,102],"show":[25],"limitations":[26],"handling":[28],"these":[29,50],"complexities.":[30],"This":[31,158],"study":[32,159],"investigates":[33],"the":[34,85,92,109,112,130,153,156,161],"effectiveness":[35,162],"neural":[37,93,164],"network":[38,94,165],"models,":[39,111],"specifically":[40],"LSTM,":[41],"Bi-LSTM":[42,131],"with":[43,132],"CRF,":[44],"BERT,":[46],"comparison":[48],"methods,":[52],"using":[53],"datasets":[54],"from":[55],"several":[56],"such":[59],"as":[60],"Turkish,":[61,122],"Finnish,":[62,138],"Hungarian,":[63],"Nahuatl,":[64],"Swahili.":[66],"The":[67,88],"methodology":[68],"includes":[69],"preprocessing":[70,145],"data":[72,76,147],"augmentation":[73,148],"improve":[75],"quality":[77],"consistency,":[79],"followed":[80],"by":[81],"training":[82],"evaluating":[84],"selected":[86],"models.":[87,142,157],"results":[89],"reveal":[90],"that":[91],"models":[95,166],"significantly":[96,139],"outperform":[97],"on":[103],"all":[104],"metrics":[105],"assessed.":[106],"Specifically,":[107],"for":[108,151,175],"BERT":[113],"model":[114],"achieved":[115],"92%":[116],"accuracy":[117],"91%":[119],"F1-score":[120],"compared":[123],"70%":[125],"67%,":[127],"respectively.":[128],"Moreover,":[129],"CRF":[133],"showed":[134],"86%":[135],"recall":[136],"outperforming":[140],"Implementing":[143],"advanced":[144],"techniques":[149],"allows":[150],"optimizing":[152],"performance":[154],"confirms":[160],"word":[168],"provides":[171],"a":[172],"valuable":[173],"framework":[174],"future":[176],"research":[177],"natural":[179],"language":[180],"processing":[181],"complex":[183],"contexts.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-10-25T00:00:00"}