{"id":"https://openalex.org/W4225986972","doi":"https://doi.org/10.1109/access.2022.3164098","title":"Domain-Specific Language Model Pre-Training for Korean Tax Law Classification","display_name":"Domain-Specific Language Model Pre-Training for Korean Tax Law Classification","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4225986972","doi":"https://doi.org/10.1109/access.2022.3164098"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3164098","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3164098","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09745941.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/ielx7/6287639/9668973/09745941.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022731366","display_name":"Yeong Hyeon Gu","orcid":"https://orcid.org/0000-0002-0002-9386"},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yeong Hyeon Gu","raw_affiliation_strings":["Department of Computer Science and Engineering, Sejong University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sejong University, Seoul, South Korea","institution_ids":["https://openalex.org/I28777354"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003668785","display_name":"Xianghua Piao","orcid":"https://orcid.org/0000-0002-2859-1661"},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Xianghua Piao","raw_affiliation_strings":["Department of Computer Science and Engineering, Sejong University, Seoul, South Korea","Department of Convergence Engineering for Intelligent Drone, Sejong University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-2859-1661","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sejong University, Seoul, South Korea","institution_ids":["https://openalex.org/I28777354"]},{"raw_affiliation_string":"Department of Convergence Engineering for Intelligent Drone, Sejong University, Seoul, South Korea","institution_ids":["https://openalex.org/I28777354"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016278134","display_name":"Helin Yin","orcid":"https://orcid.org/0000-0001-5859-4006"},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Helin Yin","raw_affiliation_strings":["Department of Computer Science and Engineering, Sejong University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sejong University, Seoul, South Korea","institution_ids":["https://openalex.org/I28777354"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069874950","display_name":"Jin Dong","orcid":"https://orcid.org/0000-0003-1131-6396"},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong Jin","raw_affiliation_strings":["Department of Computer Science and Engineering, Sejong University, Seoul, South Korea","Department of Convergence Engineering for Intelligent Drone, Sejong University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-1131-6396","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sejong University, Seoul, South Korea","institution_ids":["https://openalex.org/I28777354"]},{"raw_affiliation_string":"Department of Convergence Engineering for Intelligent Drone, Sejong University, Seoul, South Korea","institution_ids":["https://openalex.org/I28777354"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038327128","display_name":"Ri Zheng","orcid":"https://orcid.org/0000-0002-9419-068X"},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ri Zheng","raw_affiliation_strings":["Department of Computer Science and Engineering, Sejong University, Seoul, South Korea","Department of Convergence Engineering for Intelligent Drone, Sejong University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-9419-068X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sejong University, Seoul, South Korea","institution_ids":["https://openalex.org/I28777354"]},{"raw_affiliation_string":"Department of Convergence Engineering for Intelligent Drone, Sejong University, Seoul, South Korea","institution_ids":["https://openalex.org/I28777354"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064437952","display_name":"Seong Joon Yoo","orcid":"https://orcid.org/0000-0003-3447-1858"},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong Joon Yoo","raw_affiliation_strings":["Department of Computer Science and Engineering, Sejong University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sejong University, Seoul, South Korea","institution_ids":["https://openalex.org/I28777354"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5022731366"],"corresponding_institution_ids":["https://openalex.org/I28777354"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":5.7435,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.96410487,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"46342","last_page":"46353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.968999981880188,"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/T13751","display_name":"Diverse Approaches in Healthcare and Education Studies","score":0.945900022983551,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6975531578063965},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6526250243186951},{"id":"https://openalex.org/keywords/tax-law","display_name":"Tax law","score":0.6311328411102295},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4632614254951477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4453924298286438},{"id":"https://openalex.org/keywords/tax-reform","display_name":"Tax reform","score":0.41208741068840027},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.3788672387599945},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.22259896993637085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6975531578063965},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6526250243186951},{"id":"https://openalex.org/C55674860","wikidata":"https://www.wikidata.org/wiki/Q856251","display_name":"Tax law","level":3,"score":0.6311328411102295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4632614254951477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4453924298286438},{"id":"https://openalex.org/C551662922","wikidata":"https://www.wikidata.org/wiki/Q2346630","display_name":"Tax reform","level":2,"score":0.41208741068840027},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.3788672387599945},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.22259896993637085}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3164098","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3164098","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09745941.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:1f93ee65bd1b40fcbd3001d77e7b383a","is_oa":true,"landing_page_url":"https://doaj.org/article/1f93ee65bd1b40fcbd3001d77e7b383a","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 10, Pp 46342-46353 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3164098","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3164098","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09745941.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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.75}],"awards":[{"id":"https://openalex.org/G258713933","display_name":null,"funder_award_id":"2021-0-00755","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"},{"id":"https://openalex.org/G3464367310","display_name":null,"funder_award_id":"2021-0-00755","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G5781559093","display_name":null,"funder_award_id":"2021-0-00755","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225986972.pdf","grobid_xml":"https://content.openalex.org/works/W4225986972.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1538440173","https://openalex.org/W1566289585","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2950438065","https://openalex.org/W2965373594","https://openalex.org/W2970771982","https://openalex.org/W2978017171","https://openalex.org/W2997636815","https://openalex.org/W3010212250","https://openalex.org/W3032532958","https://openalex.org/W3035357591","https://openalex.org/W3035390927","https://openalex.org/W3037195933","https://openalex.org/W3038098779","https://openalex.org/W3046375318","https://openalex.org/W3047738520","https://openalex.org/W3080175947","https://openalex.org/W3091147850","https://openalex.org/W3092910147","https://openalex.org/W3098614582","https://openalex.org/W3098749165","https://openalex.org/W3103981637","https://openalex.org/W3104186312","https://openalex.org/W3117866035","https://openalex.org/W3119160044","https://openalex.org/W3119308520","https://openalex.org/W3164453494","https://openalex.org/W3185909895","https://openalex.org/W3198943295","https://openalex.org/W3198996759","https://openalex.org/W3199522085","https://openalex.org/W3208408757","https://openalex.org/W3214298066","https://openalex.org/W4287993739","https://openalex.org/W4324148013","https://openalex.org/W6632159808","https://openalex.org/W6739901393","https://openalex.org/W6766673545","https://openalex.org/W6768851824","https://openalex.org/W6769263558","https://openalex.org/W6771509786","https://openalex.org/W6771823989","https://openalex.org/W6781953712","https://openalex.org/W6801937702"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W578832185","https://openalex.org/W379073799","https://openalex.org/W637970887","https://openalex.org/W2394306283","https://openalex.org/W1573766785","https://openalex.org/W2252095989","https://openalex.org/W4398317665","https://openalex.org/W2350638601","https://openalex.org/W2464329816"],"abstract_inverted_index":{"Owing":[0],"to":[1,44,62,108,124,170,188,204],"their":[2,45],"increasing":[3],"amendments":[4],"and":[5,101,233],"complexity,":[6],"most":[7],"taxpayers":[8],"do":[9],"not":[10,58],"have":[11],"the":[12,31,65,75,126,146,155,182,206,209,215,227,234],"required":[13,123],"knowledge":[14,53],"of":[15,40,54,72,77,120,149,151,192,197,208,214,226],"tax":[16,27,41,46,55,78,114,142,152,193,199],"laws,":[17],"which":[18,60,171,221],"results":[19],"in":[20,22,64,99],"issues":[21],"everyday":[23],"life.":[24],"To":[25,134],"use":[26],"counseling":[28],"services":[29],"through":[30],"internet,":[32],"a":[33,38,49,69,83,104,117,131,158,172],"person":[34],"must":[35],"first":[36,66],"select":[37,63],"category":[39,61],"laws":[42,56,79],"corresponding":[43],"question.":[47],"However,":[48],"layperson":[50],"without":[51],"prior":[52],"may":[57],"know":[59],"place.":[67],"Therefore,":[68],"model":[70,84,162,185],"capable":[71],"automatically":[73],"classifying":[74],"categories":[76,150,191],"is":[80,96,122,130,222],"needed.":[81],"Recently,":[82],"using":[85],"BERT":[86,129],"has":[87],"been":[88],"frequently":[89],"used":[90,98,203],"for":[91,145],"text":[92],"classification;":[93],"however,":[94],"it":[95],"generally":[97],"open-domains,":[100],"often":[102],"experiences":[103],"degraded":[105],"performance":[106,207],"due":[107],"domain-specific":[109],"technical":[110],"terms,":[111],"such":[112],"as":[113],"laws.":[115],"Furthermore,":[116],"significant":[118],"amount":[119],"time":[121],"train":[125],"model,":[127],"since":[128],"large-scale":[132],"model.":[133],"address":[135],"these":[136],"issues,":[137],"this":[138],"study":[139],"proposes":[140],"Korean":[141],"law-BERT":[143],"(KTL-BERT)":[144],"automatic":[147],"classification":[148],"questions.":[153],"For":[154],"proposed":[156,210,216],"KTL-BERT,":[157],"new":[159],"pre-trained":[160,183],"language":[161,184],"was":[163,176,186,218,237],"constructed":[164],"by":[165,230],"performing":[166],"learning":[167],"from":[168],"scratch,":[169],"static":[173],"masking":[174],"method":[175],"applied":[177],"based":[178],"on":[179],"DistilRoBERTa.":[180],"Subsequently,":[181],"fine-tuned":[187],"classify":[189],"five":[190],"law.":[194],"A":[195],"total":[196],"327,735":[198],"law":[200],"questions":[201],"were":[202],"verify":[205],"KTL-BERT.":[211],"The":[212],"F1-score":[213],"KTL-BERT":[217],"approximately":[219,231,238],"91.06%,":[220],"higher":[223],"than":[224],"that":[225],"benchmark":[228],"models":[229],"1.07%-15.46%,":[232],"training":[235],"speed":[236],"0.89%-56.07%":[239],"higher.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}