{"id":"https://openalex.org/W3092557781","doi":"https://doi.org/10.15439/2020f20","title":"Overview of the Transformer-based Models for NLP Tasks","display_name":"Overview of the Transformer-based Models for NLP Tasks","publication_year":2020,"publication_date":"2020-09-26","ids":{"openalex":"https://openalex.org/W3092557781","doi":"https://doi.org/10.15439/2020f20","mag":"3092557781"},"language":"en","primary_location":{"id":"doi:10.15439/2020f20","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2020f20","pdf_url":"https://annals-csis.org/proceedings/2020/drp/pdf/20.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://annals-csis.org/proceedings/2020/drp/pdf/20.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083804718","display_name":"Anthony Gillioz","orcid":"https://orcid.org/0000-0001-7352-3708"},"institutions":[{"id":"https://openalex.org/I57825437","display_name":"University of Neuch\u00e2tel","ror":"https://ror.org/00vasag41","country_code":"CH","type":"education","lineage":["https://openalex.org/I57825437"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Anthony Gillioz","raw_affiliation_strings":["University of Neuchtel Neuchtel, Switzerland","University of Neuch\u00e2tel Neuch\u00e2tel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Neuchtel Neuchtel, Switzerland","institution_ids":["https://openalex.org/I57825437"]},{"raw_affiliation_string":"University of Neuch\u00e2tel Neuch\u00e2tel, Switzerland","institution_ids":["https://openalex.org/I57825437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021047590","display_name":"Jacky Casas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109379","display_name":"HES-SO Fribourg","ror":"https://ror.org/02kkwkt79","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891","https://openalex.org/I4210109379"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jacky Casas","raw_affiliation_strings":["University of Applied Sciences and Arts Western Switzerland Fribourg, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Applied Sciences and Arts Western Switzerland Fribourg, Switzerland","institution_ids":["https://openalex.org/I4210109379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074717197","display_name":"Elena Mugellini","orcid":"https://orcid.org/0000-0002-0775-0862"},"institutions":[{"id":"https://openalex.org/I4210109379","display_name":"HES-SO Fribourg","ror":"https://ror.org/02kkwkt79","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891","https://openalex.org/I4210109379"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Elena Mugellini","raw_affiliation_strings":["University of Applied Sciences and Arts Western Switzerland Fribourg, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Applied Sciences and Arts Western Switzerland Fribourg, Switzerland","institution_ids":["https://openalex.org/I4210109379"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067556490","display_name":"Omar Abou Khaled","orcid":"https://orcid.org/0000-0002-0178-9037"},"institutions":[{"id":"https://openalex.org/I4210109379","display_name":"HES-SO Fribourg","ror":"https://ror.org/02kkwkt79","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891","https://openalex.org/I4210109379"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Omar Abou Khaled","raw_affiliation_strings":["University of Applied Sciences and Arts Western Switzerland Fribourg, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Applied Sciences and Arts Western Switzerland Fribourg, Switzerland","institution_ids":["https://openalex.org/I4210109379"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083804718"],"corresponding_institution_ids":["https://openalex.org/I57825437"],"apc_list":null,"apc_paid":null,"fwci":13.3371,"has_fulltext":true,"cited_by_count":384,"citation_normalized_percentile":{"value":0.99137811,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"21","issue":null,"first_page":"179","last_page":"183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9872000217437744,"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/transformer","display_name":"Transformer","score":0.8052619695663452},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.7859629392623901},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7184890508651733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5653716325759888},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5508796572685242},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5000646114349365},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44594162702560425},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4335380792617798},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3530399799346924},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32301485538482666},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15746766328811646},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08472108840942383},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07046973705291748},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06281676888465881}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8052619695663452},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.7859629392623901},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7184890508651733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5653716325759888},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5508796572685242},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5000646114349365},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44594162702560425},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4335380792617798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3530399799346924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32301485538482666},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15746766328811646},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08472108840942383},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07046973705291748},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06281676888465881},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.15439/2020f20","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2020f20","pdf_url":"https://annals-csis.org/proceedings/2020/drp/pdf/20.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:doaj.org/article:ff3773c8df064a129a070fc5731598c9","is_oa":false,"landing_page_url":"https://doaj.org/article/ff3773c8df064a129a070fc5731598c9","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annals of computer science and information systems, Vol 21, Pp 179-183 (2020)","raw_type":"article"},{"id":"pmh:oai:hesso.tind.io:6812","is_oa":false,"landing_page_url":"http://arodes.hes-so.ch/record/6812","pdf_url":null,"source":{"id":"https://openalex.org/S4306402432","display_name":"ArODES (HES-SO (https://www.hes-so.ch/))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210088449","host_organization_name":"HES-SO Gen\u00e8ve","host_organization_lineage":["https://openalex.org/I4210088449"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arodes.hes-so.ch/record/6812","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.15439/2020f20","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2020f20","pdf_url":"https://annals-csis.org/proceedings/2020/drp/pdf/20.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3092557781.pdf","grobid_xml":"https://content.openalex.org/works/W3092557781.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1614298861","https://openalex.org/W1689711448","https://openalex.org/W1816313093","https://openalex.org/W1843891098","https://openalex.org/W2064675550","https://openalex.org/W2119168550","https://openalex.org/W2157331557","https://openalex.org/W2250539671","https://openalex.org/W2523469089","https://openalex.org/W2606964149","https://openalex.org/W2799054028","https://openalex.org/W2805206884","https://openalex.org/W2885185669","https://openalex.org/W2896457183","https://openalex.org/W2911109671","https://openalex.org/W2912521296","https://openalex.org/W2913129712","https://openalex.org/W2914120296","https://openalex.org/W2914526845","https://openalex.org/W2920812691","https://openalex.org/W2923014074","https://openalex.org/W2931316642","https://openalex.org/W2943552823","https://openalex.org/W2950577311","https://openalex.org/W2950813464","https://openalex.org/W2962784628","https://openalex.org/W2962965405","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/W2963854351","https://openalex.org/W2964110616","https://openalex.org/W2964268978","https://openalex.org/W2965210982","https://openalex.org/W2965373594","https://openalex.org/W2970119519","https://openalex.org/W2970597249","https://openalex.org/W2971008823","https://openalex.org/W2975059944","https://openalex.org/W2978017171","https://openalex.org/W2981851019","https://openalex.org/W2986154550","https://openalex.org/W2990188683","https://openalex.org/W2990704537","https://openalex.org/W2994673210","https://openalex.org/W2994980856","https://openalex.org/W2996428491","https://openalex.org/W2996580882","https://openalex.org/W2997200074","https://openalex.org/W3032532958","https://openalex.org/W3088059392","https://openalex.org/W4287760320","https://openalex.org/W4295838474","https://openalex.org/W4299567010","https://openalex.org/W4385245566","https://openalex.org/W4394650345","https://openalex.org/W6637409405","https://openalex.org/W6691431627","https://openalex.org/W6718053083","https://openalex.org/W6739901393","https://openalex.org/W6758657797","https://openalex.org/W6763240421","https://openalex.org/W6770131634","https://openalex.org/W6771626834"],"related_works":["https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3100913109","https://openalex.org/W3198458223","https://openalex.org/W3126642501","https://openalex.org/W2964413124"],"abstract_inverted_index":{"proposed":[0],"a":[1,42,93],"new":[2],"neural":[3],"network":[4],"architecture":[5,10,27,88],"named":[6],"Transformer.":[7],"That":[8],"modern":[9],"quickly":[11],"revolutionized":[12],"the":[13,31,37,47,69,74,86],"natural":[14],"language":[15],"processing":[16],"world.":[17],"Models":[18],"like":[19,98],"GPT":[20],"and":[21,66,81,92],"BERT":[22,91],"relying":[23],"on":[24,55],"this":[25,60],"Transformer":[26],"have":[28],"fully":[29],"outperformed":[30],"previous":[32],"state-of-theart":[33],"networks.":[34],"It":[35],"surpassed":[36],"earlier":[38],"approaches":[39],"by":[40],"such":[41,77,89],"wide":[43],"margin":[44],"that":[45],"all":[46],"recent":[48],"cutting":[49],"edge":[50],"models":[51,76,97],"seem":[52],"to":[53],"rely":[54],"these":[56],"Transformer-based":[57],"architectures.":[58],"In":[59],"paper,":[61],"we":[62],"provide":[63],"an":[64],"overview":[65],"explanations":[67],"of":[68,95],"latest":[70],"models.":[71],"We":[72],"cover":[73],"auto-regressive":[75],"as":[78,83,85,90],"GPT,":[79],"GPT-2":[80],"XLNET,":[82],"well":[84],"auto-encoder":[87],"lot":[94],"post-BERT":[96],"RoBERTa,":[99],"ALBERT,":[100],"ERNIE":[101],"1.0/2.0.":[102]},"counts_by_year":[{"year":2026,"cited_by_count":29},{"year":2025,"cited_by_count":114},{"year":2024,"cited_by_count":125},{"year":2023,"cited_by_count":81},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}