{"id":"https://openalex.org/W3159795318","doi":"https://doi.org/10.1109/icpr48806.2021.9412023","title":"KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding","display_name":"KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3159795318","doi":"https://doi.org/10.1109/icpr48806.2021.9412023","mag":"3159795318"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100768432","display_name":"Hyunjae Lee","orcid":"https://orcid.org/0000-0003-1954-8124"},"institutions":[{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]},{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyunjae Lee","raw_affiliation_strings":["Samsung SDS"],"affiliations":[{"raw_affiliation_string":"Samsung SDS","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111803091","display_name":"Jaewoong Yoon","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewoong Yoon","raw_affiliation_strings":["Samsung SDS"],"affiliations":[{"raw_affiliation_string":"Samsung SDS","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086090272","display_name":"Bonggyu Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bonggyu Hwang","raw_affiliation_strings":["Samsung SDS"],"affiliations":[{"raw_affiliation_string":"Samsung SDS","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042704383","display_name":"Seongho Joe","orcid":null},"institutions":[{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]},{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongho Joe","raw_affiliation_strings":["Samsung SDS"],"affiliations":[{"raw_affiliation_string":"Samsung SDS","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081601034","display_name":"Seung-Jai Min","orcid":null},"institutions":[{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]},{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungjai Min","raw_affiliation_strings":["Samsung SDS"],"affiliations":[{"raw_affiliation_string":"Samsung SDS","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012323997","display_name":"Youngjune Gwon","orcid":null},"institutions":[{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]},{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjune Gwon","raw_affiliation_strings":["Samsung SDS"],"affiliations":[{"raw_affiliation_string":"Samsung SDS","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100768432"],"corresponding_institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"],"apc_list":null,"apc_paid":null,"fwci":1.4956,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85385261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5551","last_page":"5557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T13629","display_name":"Text Readability and Simplification","score":0.9803000092506409,"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":0.8306007981300354},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7445957660675049},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7026979923248291},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6276969313621521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6274689435958862},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6054552793502808},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.5708017349243164},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5457035303115845},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5276628732681274},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4193822741508484},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3866897225379944},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24592339992523193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8306007981300354},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7445957660675049},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7026979923248291},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6276969313621521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6274689435958862},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6054552793502808},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.5708017349243164},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5457035303115845},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5276628732681274},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4193822741508484},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3866897225379944},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24592339992523193},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W638387498","https://openalex.org/W2113459411","https://openalex.org/W2130942839","https://openalex.org/W2144578941","https://openalex.org/W2270070752","https://openalex.org/W2462831000","https://openalex.org/W2606964149","https://openalex.org/W2798955519","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2930786691","https://openalex.org/W2963250244","https://openalex.org/W2963310665","https://openalex.org/W2963323070","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963748441","https://openalex.org/W2963846996","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2980282514","https://openalex.org/W2982399380","https://openalex.org/W2983040767","https://openalex.org/W2986154550","https://openalex.org/W2990188683","https://openalex.org/W2995230342","https://openalex.org/W2995647371","https://openalex.org/W2996428491","https://openalex.org/W2996580882","https://openalex.org/W3011411500","https://openalex.org/W3015296018","https://openalex.org/W3032532958","https://openalex.org/W3034999214","https://openalex.org/W3035390927","https://openalex.org/W3102927624","https://openalex.org/W3210120707","https://openalex.org/W4285719527","https://openalex.org/W4287993739","https://openalex.org/W4385245566","https://openalex.org/W6676984168","https://openalex.org/W6679436768","https://openalex.org/W6718683173","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6760810938","https://openalex.org/W6763701032","https://openalex.org/W6765807869","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6768817161","https://openalex.org/W6775691588","https://openalex.org/W6802852670","https://openalex.org/W7029390631"],"related_works":["https://openalex.org/W2367925007","https://openalex.org/W3015724364","https://openalex.org/W4288263119","https://openalex.org/W2967994095","https://openalex.org/W2900126711","https://openalex.org/W4285240985","https://openalex.org/W4225162083","https://openalex.org/W3202115945","https://openalex.org/W2542958340","https://openalex.org/W4389520438"],"abstract_inverted_index":{"A":[0],"Lite":[1],"BERT":[2,104],"(ALBERT)":[3],"has":[4],"been":[5],"introduced":[6],"to":[7,18,39,82,97,124,141],"scale":[8],"up":[9],"deep":[10],"bidirectional":[11],"representation":[12],"learning":[13],"for":[14,25,58,132,147],"natural":[15],"languages.":[16],"Due":[17],"the":[19,28,33,40,76,83,113],"lack":[20],"of":[21],"pretrained":[22,100,136],"ALBERT":[23,55],"models":[24],"Korean":[26,59,133,148],"language,":[27],"best":[29],"available":[30,140],"practice":[31],"is":[32,138],"multilingual":[34],"model":[35,56,87,93],"or":[36],"resorting":[37],"back":[38],"any":[41],"other":[42],"BERT-based":[43],"model.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"develop":[49],"and":[50,73,79,86,144],"pretrain":[51],"KoreALBERT,":[52],"a":[53,64],"monolingual":[54],"specifically":[57],"language":[60],"understanding.":[61],"We":[62],"introduce":[63],"new":[65],"training":[66],"objective,":[67],"namely":[68],"Word":[69],"Order":[70],"Prediction":[71],"(WOP),":[72],"use":[74],"alongside":[75],"existing":[77],"MLM":[78],"SOP":[80],"criteria":[81],"same":[84],"architecture":[85],"parameters.":[88],"Despite":[89],"having":[90],"significantly":[91],"fewer":[92],"parameters":[94],"(thus,":[95],"quicker":[96],"train),":[98],"our":[99],"KoreALBERT":[101,122,137],"outperforms":[102],"its":[103],"counterpart":[105],"on":[106],"6":[107],"different":[108],"NLU":[109],"tasks.":[110],"Consistent":[111],"with":[112],"empirical":[114],"results":[115],"in":[116],"English":[117],"by":[118],"Lan":[119],"et":[120],"al.,":[121],"seems":[123],"improve":[125],"downstream":[126],"task":[127],"performance":[128],"involving":[129],"multi-sentence":[130],"encoding":[131],"language.":[134],"The":[135],"publicly":[139],"encourage":[142],"research":[143],"application":[145],"development":[146],"NLP.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-23T23:15:26.331081","created_date":"2025-10-10T00:00:00"}