{"id":"https://openalex.org/W4394730918","doi":"https://doi.org/10.1109/access.2024.3387860","title":"Data Augmentation With Semantic Enrichment for Deep Learning Invoice Text Classification","display_name":"Data Augmentation With Semantic Enrichment for Deep Learning Invoice Text Classification","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394730918","doi":"https://doi.org/10.1109/access.2024.3387860"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3387860","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3387860","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10496671.pdf","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":null,"license_id":null,"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://ieeexplore.ieee.org/ielx7/6287639/6514899/10496671.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wei Wen Chi","orcid":null},"institutions":[{"id":"https://openalex.org/I84339108","display_name":"Sunway University","ror":"https://ror.org/04mjt7f73","country_code":"MY","type":"education","lineage":["https://openalex.org/I84339108"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Wei Wen Chi","raw_affiliation_strings":["Department of Business Analytics, Sunway Business School, Sunway University, Bandar Sunway, Selangor, Malaysia","Department of Business Analytics, Sunway Business School, Sunway University, 5, Jalan University, Petaling Jaya, Bandar Sunway, Selangor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Business Analytics, Sunway Business School, Sunway University, Bandar Sunway, Selangor, Malaysia","institution_ids":["https://openalex.org/I84339108"]},{"raw_affiliation_string":"Department of Business Analytics, Sunway Business School, Sunway University, 5, Jalan University, Petaling Jaya, Bandar Sunway, Selangor, Malaysia","institution_ids":["https://openalex.org/I84339108"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056370378","display_name":"Tiong Yew Tang","orcid":"https://orcid.org/0000-0003-3891-1398"},"institutions":[{"id":"https://openalex.org/I84339108","display_name":"Sunway University","ror":"https://ror.org/04mjt7f73","country_code":"MY","type":"education","lineage":["https://openalex.org/I84339108"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Tiong Yew Tang","raw_affiliation_strings":["Department of Business Analytics, Sunway Business School, Sunway University, Bandar Sunway, Selangor, Malaysia","Department of Business Analytics, Sunway Business School, Sunway University, 5, Jalan University, Petaling Jaya, Bandar Sunway, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-3891-1398","affiliations":[{"raw_affiliation_string":"Department of Business Analytics, Sunway Business School, Sunway University, Bandar Sunway, Selangor, Malaysia","institution_ids":["https://openalex.org/I84339108"]},{"raw_affiliation_string":"Department of Business Analytics, Sunway Business School, Sunway University, 5, Jalan University, Petaling Jaya, Bandar Sunway, Selangor, Malaysia","institution_ids":["https://openalex.org/I84339108"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000838447","display_name":"Narishah Mohamed Salleh","orcid":"https://orcid.org/0000-0002-9834-9731"},"institutions":[{"id":"https://openalex.org/I84339108","display_name":"Sunway University","ror":"https://ror.org/04mjt7f73","country_code":"MY","type":"education","lineage":["https://openalex.org/I84339108"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Narishah Mohamed Salleh","raw_affiliation_strings":["Department of Business Analytics, Sunway Business School, Sunway University, Bandar Sunway, Selangor, Malaysia","Department of Business Analytics, Sunway Business School, Sunway University, 5, Jalan University, Petaling Jaya, Bandar Sunway, Selangor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Business Analytics, Sunway Business School, Sunway University, Bandar Sunway, Selangor, Malaysia","institution_ids":["https://openalex.org/I84339108"]},{"raw_affiliation_string":"Department of Business Analytics, Sunway Business School, Sunway University, 5, Jalan University, Petaling Jaya, Bandar Sunway, Selangor, Malaysia","institution_ids":["https://openalex.org/I84339108"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080001475","display_name":"Muaadh Mukred","orcid":"https://orcid.org/0000-0001-6826-8458"},"institutions":[{"id":"https://openalex.org/I84339108","display_name":"Sunway University","ror":"https://ror.org/04mjt7f73","country_code":"MY","type":"education","lineage":["https://openalex.org/I84339108"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Muaadh Mukred","raw_affiliation_strings":["Department of Business Analytics, Sunway Business School, Sunway University, Bandar Sunway, Selangor, Malaysia","Department of Business Analytics, Sunway Business School, Sunway University, 5, Jalan University, Petaling Jaya, Bandar Sunway, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0000-0001-6826-8458","affiliations":[{"raw_affiliation_string":"Department of Business Analytics, Sunway Business School, Sunway University, Bandar Sunway, Selangor, Malaysia","institution_ids":["https://openalex.org/I84339108"]},{"raw_affiliation_string":"Department of Business Analytics, Sunway Business School, Sunway University, 5, Jalan University, Petaling Jaya, Bandar Sunway, Selangor, Malaysia","institution_ids":["https://openalex.org/I84339108"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089641116","display_name":"Hussain AlSalman","orcid":"https://orcid.org/0000-0001-8172-4964"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Hussain AlSalman","raw_affiliation_strings":["Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-8172-4964","affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014131945","display_name":"Muhammad Zohaib","orcid":"https://orcid.org/0000-0002-2061-7716"},"institutions":[{"id":"https://openalex.org/I63548447","display_name":"Lappeenranta-Lahti University of Technology","ror":"https://ror.org/0208vgz68","country_code":"FI","type":"education","lineage":["https://openalex.org/I63548447"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Muhammad Zohaib","raw_affiliation_strings":["Software Engineering Department, Lappeenranta-Lahti University of Technology, Lappeenranta, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Engineering Department, Lappeenranta-Lahti University of Technology, Lappeenranta, Finland","institution_ids":["https://openalex.org/I63548447"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84339108"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.1992,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92495739,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"57326","last_page":"57344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9810000061988831,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9810000061988831,"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/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9799000024795532,"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":0.8474584221839905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7995508313179016},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.6932712197303772},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6586092114448547},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5117642879486084},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4778865575790405},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.46825891733169556},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4287766218185425},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3306421637535095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32018226385116577},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1824105679988861}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8474584221839905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7995508313179016},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.6932712197303772},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6586092114448547},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5117642879486084},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4778865575790405},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.46825891733169556},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4287766218185425},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3306421637535095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32018226385116577},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1824105679988861}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3387860","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3387860","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10496671.pdf","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e8dbfde7826343fb8a0da3fa22534cb4","is_oa":true,"landing_page_url":"https://doaj.org/article/e8dbfde7826343fb8a0da3fa22534cb4","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,"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 57326-57344 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3387860","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3387860","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10496671.pdf","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G127140080","display_name":null,"funder_award_id":"RSP2024R244","funder_id":"https://openalex.org/F4320321145","funder_display_name":"King Saud University"}],"funders":[{"id":"https://openalex.org/F4320321145","display_name":"King Saud University","ror":"https://ror.org/02f81g417"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394730918.pdf","grobid_xml":"https://content.openalex.org/works/W4394730918.grobid-xml"},"referenced_works_count":106,"referenced_works":["https://openalex.org/W141057188","https://openalex.org/W1493036841","https://openalex.org/W1498436455","https://openalex.org/W1524688041","https://openalex.org/W1538989194","https://openalex.org/W1715319291","https://openalex.org/W1855281999","https://openalex.org/W1964660623","https://openalex.org/W1965498893","https://openalex.org/W1967065942","https://openalex.org/W1971129545","https://openalex.org/W1973610950","https://openalex.org/W1974339500","https://openalex.org/W1979346010","https://openalex.org/W1985258458","https://openalex.org/W1985697096","https://openalex.org/W1992113527","https://openalex.org/W2002306339","https://openalex.org/W2007431958","https://openalex.org/W2009190245","https://openalex.org/W2015452969","https://openalex.org/W2015547952","https://openalex.org/W2021774695","https://openalex.org/W2023639956","https://openalex.org/W2039958785","https://openalex.org/W2040870580","https://openalex.org/W2042432758","https://openalex.org/W2048610319","https://openalex.org/W2048658075","https://openalex.org/W2064675550","https://openalex.org/W2066393862","https://openalex.org/W2071718761","https://openalex.org/W2079735306","https://openalex.org/W2081580037","https://openalex.org/W2082729696","https://openalex.org/W2084846039","https://openalex.org/W2087404238","https://openalex.org/W2087660232","https://openalex.org/W2088920469","https://openalex.org/W2092246763","https://openalex.org/W2102381086","https://openalex.org/W2106022904","https://openalex.org/W2106136950","https://openalex.org/W2107605823","https://openalex.org/W2107827038","https://openalex.org/W2107878631","https://openalex.org/W2108564850","https://openalex.org/W2117812871","https://openalex.org/W2118020653","https://openalex.org/W2118023920","https://openalex.org/W2119191234","https://openalex.org/W2139317750","https://openalex.org/W2148143831","https://openalex.org/W2150102617","https://openalex.org/W2150272696","https://openalex.org/W2153686960","https://openalex.org/W2156909104","https://openalex.org/W2166347079","https://openalex.org/W2169384781","https://openalex.org/W2169821025","https://openalex.org/W2250539671","https://openalex.org/W2581151040","https://openalex.org/W2592751531","https://openalex.org/W2782127670","https://openalex.org/W2896457183","https://openalex.org/W2906164196","https://openalex.org/W2921575332","https://openalex.org/W2941799245","https://openalex.org/W2947630478","https://openalex.org/W2971296908","https://openalex.org/W2990129687","https://openalex.org/W2990288623","https://openalex.org/W2991113277","https://openalex.org/W3013984202","https://openalex.org/W3034156543","https://openalex.org/W3034698100","https://openalex.org/W3076947077","https://openalex.org/W3088085086","https://openalex.org/W3091692095","https://openalex.org/W3096650070","https://openalex.org/W3097917088","https://openalex.org/W3129207397","https://openalex.org/W3132259035","https://openalex.org/W3152268000","https://openalex.org/W3155464240","https://openalex.org/W3156881285","https://openalex.org/W3165846270","https://openalex.org/W3176398418","https://openalex.org/W3176923149","https://openalex.org/W3183771288","https://openalex.org/W3194005300","https://openalex.org/W3195189374","https://openalex.org/W3212007445","https://openalex.org/W3214193653","https://openalex.org/W3215255094","https://openalex.org/W4220866756","https://openalex.org/W4230799834","https://openalex.org/W4236521339","https://openalex.org/W4280503842","https://openalex.org/W4297094638","https://openalex.org/W6632181731","https://openalex.org/W6637521844","https://openalex.org/W6675966996","https://openalex.org/W6681875376","https://openalex.org/W6681961571","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W3099765033"],"abstract_inverted_index":{"Natural":[0],"language":[1],"processing":[2],"(NLP)":[3],"is":[4],"a":[5],"research":[6,21],"field":[7],"that":[8],"provides":[9],"huge":[10],"potential":[11],"to":[12,47,171],"automate":[13],"accounting":[14],"tasks":[15],"dealing":[16],"with":[17,81,112,145],"text":[18,35,58],"data.":[19],"This":[20],"studies":[22],"the":[23,33,49,55,137,146,150],"application":[24],"of":[25,63,168],"NLP":[26,50],"in":[27],"automatically":[28],"categorizing":[29],"invoices":[30],"based":[31],"on":[32],"invoice":[34,64],"description.":[36],"The":[37],"study":[38],"employs":[39],"semantic":[40],"enrichment,":[41],"data":[42,77],"augmentation,":[43],"and":[44,59,117,134,158,178],"deep":[45,119],"learning":[46,115,120],"address":[48],"unique":[51],"issues":[52],"posed":[53],"by":[54],"inherent":[56],"short":[57],"multi-class":[60],"imbalance":[61],"nature":[62],"descriptions.":[65],"Semantic":[66],"enrichment":[67],"was":[68,78,107],"done":[69],"using":[70],"labels":[71],"as":[72],"an":[73,166],"information":[74],"source.":[75],"Training":[76],"artificially":[79],"increased":[80],"either":[82],"WordNet":[83,140],"synonym":[84],"replacement,":[85,93],"Global":[86],"Vectors":[87],"for":[88,110,174,183],"Word":[89],"Representation":[90],"(GloVe)":[91],"word":[92,101],"or":[94],"Bidirectional":[95,129],"Encoder":[96],"Representations":[97],"from":[98],"Transformers":[99],"(BERT)":[100],"replacement":[102],"method.":[103],"Each":[104],"training":[105,111,142],"dataset":[106],"then":[108],"supplied":[109],"one":[113],"nondeep":[114],"classifier":[116,148],"two":[118],"classifiers":[121],"respectively,":[122],"namely":[123],"Linear":[124],"Support":[125],"Vector":[126],"Machine":[127],"(LSVM),":[128],"Long":[130],"Short-Term":[131],"Memory":[132],"(Bi-LSTM),":[133],"BERT.":[135],"Overall,":[136],"semantically":[138],"enriched,":[139],"augmented":[141],"set":[143],"paired":[144],"BERT":[147],"yielded":[149],"best":[151],"results,":[152],"successfully":[153],"preserving":[154],"semantics,":[155],"reducing":[156],"noise":[157],"overfitting":[159],"while":[160],"improving":[161],"accuracy":[162],"per":[163],"class,":[164],"achieving":[165],"increase":[167],"performance":[169],"up":[170],"20":[172],"ppts":[173],"macro":[175],"F1":[176],"score":[177],"6.7":[179],"percentage":[180],"points":[181],"(ppts)":[182],"accuracy.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-14T08:36:36.166977","created_date":"2025-10-10T00:00:00"}