{"id":"https://openalex.org/W3114453204","doi":"https://doi.org/10.1109/kse50997.2020.9287406","title":"From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection","display_name":"From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection","publication_year":2020,"publication_date":"2020-11-12","ids":{"openalex":"https://openalex.org/W3114453204","doi":"https://doi.org/10.1109/kse50997.2020.9287406","mag":"3114453204"},"language":"en","primary_location":{"id":"doi:10.1109/kse50997.2020.9287406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse50997.2020.9287406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 12th International Conference on Knowledge and Systems Engineering (KSE)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.12162","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Quang Huu Pham","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Quang Huu Pham","raw_affiliation_strings":["R&D Lab, Sun Asterisk Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R&D Lab, Sun Asterisk Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114861020","display_name":"Viet Anh Nguyen","orcid":"https://orcid.org/0000-0002-8981-4638"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viet Anh Nguyen","raw_affiliation_strings":["R&D Lab, Sun Asterisk Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R&D Lab, Sun Asterisk Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064509843","display_name":"Linh Bao Doan","orcid":"https://orcid.org/0000-0001-8579-9808"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linh Bao Doan","raw_affiliation_strings":["R&D Lab, Sun Asterisk Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R&D Lab, Sun Asterisk Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083505237","display_name":"Ngoc Tran","orcid":"https://orcid.org/0000-0003-0479-9561"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ngoc N. Tran","raw_affiliation_strings":["R&D Lab, Sun Asterisk Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R&D Lab, Sun Asterisk Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040778937","display_name":"T\u1ea1 Minh Thanh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ta Minh Thanh","raw_affiliation_strings":["R&D Lab, Sun Asterisk Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R&D Lab, Sun Asterisk Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7679,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88474692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"2","issue":null,"first_page":"37","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","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/T12262","display_name":"Hate Speech and Cyberbullying Detection","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":0.9140999913215637,"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":0.7767183780670166},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6545417904853821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6494309902191162},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6230219006538391},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5508454442024231},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.5481489300727844},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49958348274230957},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4976244270801544},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.49342337250709534},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4428226351737976},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42973482608795166},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4200073182582855},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07526925206184387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767183780670166},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6545417904853821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6494309902191162},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6230219006538391},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5508454442024231},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.5481489300727844},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49958348274230957},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4976244270801544},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.49342337250709534},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4428226351737976},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42973482608795166},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4200073182582855},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07526925206184387},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/kse50997.2020.9287406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse50997.2020.9287406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 12th International Conference on Knowledge and Systems Engineering (KSE)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.12162","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.12162","pdf_url":"https://arxiv.org/pdf/2102.12162","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.12162","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.12162","pdf_url":"https://arxiv.org/pdf/2102.12162","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W205930466","https://openalex.org/W1071251684","https://openalex.org/W1492737170","https://openalex.org/W1614298861","https://openalex.org/W1997326096","https://openalex.org/W2044173330","https://openalex.org/W2045343360","https://openalex.org/W2047449974","https://openalex.org/W2123442489","https://openalex.org/W2160685721","https://openalex.org/W2164628858","https://openalex.org/W2181854537","https://openalex.org/W2247662608","https://openalex.org/W2250539671","https://openalex.org/W2311430799","https://openalex.org/W2340954483","https://openalex.org/W2399587463","https://openalex.org/W2473555522","https://openalex.org/W2564933006","https://openalex.org/W2604821579","https://openalex.org/W2613977835","https://openalex.org/W2741065173","https://openalex.org/W2756354991","https://openalex.org/W2806872289","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2948210185","https://openalex.org/W2963026768","https://openalex.org/W2965373594","https://openalex.org/W2973806433","https://openalex.org/W3007955273","https://openalex.org/W3042012685","https://openalex.org/W3098637735","https://openalex.org/W3103061166","https://openalex.org/W4294367149","https://openalex.org/W4298857067","https://openalex.org/W4300847054","https://openalex.org/W4385245566","https://openalex.org/W4394658982","https://openalex.org/W6608482188","https://openalex.org/W6636510571","https://openalex.org/W6684107795","https://openalex.org/W6713042285","https://openalex.org/W6739901393","https://openalex.org/W6747248625","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6766673545","https://openalex.org/W6780317240","https://openalex.org/W6864772185"],"related_works":["https://openalex.org/W2901286616","https://openalex.org/W2291461084","https://openalex.org/W2050882094","https://openalex.org/W3113733647","https://openalex.org/W4206924063","https://openalex.org/W3042674643","https://openalex.org/W1844055093","https://openalex.org/W1972594981","https://openalex.org/W2136542423","https://openalex.org/W2045966063"],"abstract_inverted_index":{"Natural":[0],"language":[1,25,52,58,98],"processing":[2],"(NLP)":[3],"is":[4],"a":[5,21,56,68,91,101,178],"fast-growing":[6],"field":[7],"of":[8,24,74,80],"artificial":[9],"intelligence.":[10],"Since":[11],"the":[12,75,95,113,124,127,174],"Transformer":[13],"[32]":[14],"was":[15],"introduced":[16],"by":[17,36,122],"Google":[18],"in":[19],"2017,":[20],"large":[22],"number":[23],"models":[26,40],"such":[27,77],"as":[28,78],"BERT,":[29],"GPT,":[30],"and":[31,46,83,163],"ELMo":[32],"have":[33],"been":[34],"inspired":[35],"this":[37,87],"architecture.":[38],"These":[39],"were":[41],"trained":[42],"on":[43,50,60,119,126,181],"huge":[44],"datasets":[45,63,76],"achieved":[47],"state-of-the-art":[48,180],"results":[49],"natural":[51],"understanding.":[53],"However,":[54],"fine-tuning":[55],"pre-trained":[57,145],"model":[59,99,125],"much":[61],"smaller":[62],"for":[64,138],"downstream":[65],"tasks":[66],"requires":[67],"carefully-designed":[69],"pipeline":[70,92,172],"to":[71,93,100,143],"mitigate":[72],"problems":[73],"lack":[79],"training":[81,156],"data":[82],"imbalanced":[84],"data.":[85],"In":[86,141],"paper,":[88],"we":[89,134,152],"propose":[90],"adapt":[94],"general-purpose":[96],"RoBERTa":[97],"specific":[102],"text":[103,139],"classification":[104],"task:":[105],"Vietnamese":[106,182],"Hate":[107,183],"Speech":[108,184],"Detection.":[109],"We":[110],"first":[111],"tune":[112],"PhoBERT":[114],"<sup":[115,188],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[116,189],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[117],"[9]":[118],"our":[120,170],"dataset":[121],"re-training":[123],"Masked":[128],"Language":[129],"Model":[130],"(MLM)":[131],"task;":[132],"then,":[133],"employ":[135],"its":[136],"encoder":[137],"classification.":[140],"order":[142],"preserve":[144],"weights":[146],"while":[147],"learning":[148,161],"new":[149,179],"feature":[150],"representations,":[151],"further":[153],"utilize":[154],"different":[155],"techniques:":[157],"layer":[158],"freezing,":[159],"block-wise":[160],"rate,":[162],"label":[164],"smoothing.":[165],"Our":[166],"experiments":[167],"proved":[168],"that":[169],"proposed":[171],"boosts":[173],"performance":[175],"significantly,":[176],"achieving":[177],"Detection":[185],"(HSD)":[186],"campaign":[187],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[190],"with":[191],"0.7221":[192],"F1":[193],"score.":[194]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-30T09:15:22.047038","created_date":"2021-01-05T00:00:00"}