{"id":"https://openalex.org/W3200784729","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534117","title":"Exploring the structure of BERT through Kernel Learning","display_name":"Exploring the structure of BERT through Kernel Learning","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200784729","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534117","mag":"3200784729"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5061388105","display_name":"Ivano Lauriola","orcid":"https://orcid.org/0000-0001-7236-061X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ivano Lauriola","raw_affiliation_strings":["Amazon Alexa AI, University of Padova"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, University of Padova","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073069826","display_name":"Alberto Lavelli","orcid":"https://orcid.org/0000-0002-7175-6804"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Lavelli","raw_affiliation_strings":["Fondazione Bruno Kessler, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler, Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056376686","display_name":"Alessandro Moschitti","orcid":"https://orcid.org/0000-0003-2216-8034"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alessandro Moschitti","raw_affiliation_strings":["Amazon Alexa AI Manhattan, Beach, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI Manhattan, Beach, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036243123","display_name":"Fabio Aiolli","orcid":"https://orcid.org/0000-0002-5823-7540"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Aiolli","raw_affiliation_strings":["University of Padova, Padova, Italy"],"affiliations":[{"raw_affiliation_string":"University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061388105"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13249924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"12","issue":null,"first_page":"1","last_page":"9"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7827540636062622},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7623399496078491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7279344201087952},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5679126977920532},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5400773286819458},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4524364471435547},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44616031646728516},{"id":"https://openalex.org/keywords/multiple-kernel-learning","display_name":"Multiple kernel learning","score":0.4425990879535675},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.3232092261314392},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13100841641426086},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12990152835845947},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08377149701118469}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7827540636062622},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7623399496078491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279344201087952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5679126977920532},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5400773286819458},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4524364471435547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44616031646728516},{"id":"https://openalex.org/C2776879701","wikidata":"https://www.wikidata.org/wiki/Q25048660","display_name":"Multiple kernel learning","level":4,"score":0.4425990879535675},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.3232092261314392},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13100841641426086},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12990152835845947},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08377149701118469},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.research.unipd.it:11577/3440276","is_oa":false,"landing_page_url":"http://hdl.handle.net/11577/3440276","pdf_url":null,"source":{"id":"https://openalex.org/S4377196283","display_name":"Research Padua  Archive (University of Padua)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1510073064","https://openalex.org/W1559159361","https://openalex.org/W1817277359","https://openalex.org/W1901129140","https://openalex.org/W2020816856","https://openalex.org/W2060166505","https://openalex.org/W2067624665","https://openalex.org/W2109743529","https://openalex.org/W2113459411","https://openalex.org/W2114524997","https://openalex.org/W2156909104","https://openalex.org/W2166353267","https://openalex.org/W2288122362","https://openalex.org/W2542192908","https://openalex.org/W2551469986","https://openalex.org/W2743028754","https://openalex.org/W2765331439","https://openalex.org/W2767691613","https://openalex.org/W2782213427","https://openalex.org/W2896457183","https://openalex.org/W2910243263","https://openalex.org/W2911489562","https://openalex.org/W2917049430","https://openalex.org/W2929096990","https://openalex.org/W2948947170","https://openalex.org/W2952861497","https://openalex.org/W2962739339","https://openalex.org/W2962815673","https://openalex.org/W2962992847","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964303116","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2971134012","https://openalex.org/W2972312591","https://openalex.org/W2973154008","https://openalex.org/W2973827203","https://openalex.org/W2977057303","https://openalex.org/W2978017171","https://openalex.org/W2980508402","https://openalex.org/W2982567551","https://openalex.org/W2990070951","https://openalex.org/W2996798951","https://openalex.org/W2997090102","https://openalex.org/W3002784191","https://openalex.org/W3029497709","https://openalex.org/W3102568136","https://openalex.org/W3118485687","https://openalex.org/W4206686222","https://openalex.org/W4288104408","https://openalex.org/W4288631803","https://openalex.org/W4385245566","https://openalex.org/W6638480814","https://openalex.org/W6639824700","https://openalex.org/W6676984168","https://openalex.org/W6684161873","https://openalex.org/W6739901393","https://openalex.org/W6747652377","https://openalex.org/W6755207826","https://openalex.org/W6757883768","https://openalex.org/W6760499460","https://openalex.org/W6763701032","https://openalex.org/W6766673545","https://openalex.org/W6767665982","https://openalex.org/W6768179808","https://openalex.org/W6768851824","https://openalex.org/W6769001469","https://openalex.org/W6769318315","https://openalex.org/W6778161486"],"related_works":["https://openalex.org/W2900715739","https://openalex.org/W2289496068","https://openalex.org/W2547116720","https://openalex.org/W2043864454","https://openalex.org/W2188831877","https://openalex.org/W3125885229","https://openalex.org/W4291669689","https://openalex.org/W2153379791","https://openalex.org/W2001173190","https://openalex.org/W2295320501"],"abstract_inverted_index":{"Combining":[0],"internal":[1,21,62,110],"representations":[2,22,63,106],"of":[3,32,35,64,79,112,140],"a":[4,33,38,56,65,85,97,125],"pre-trained":[5],"Transformer":[6,66,87,114,135],"model,":[7],"such":[8],"as":[9,124],"the":[10,46,51,75,91,109,113,122,130,134,138],"popular":[11],"BERT,":[12],"is":[13,84,96],"an":[14],"interesting":[15],"and":[16,104,115],"challenging":[17],"task":[18],"nowadays.":[19],"Usually,":[20],"are":[23],"combined":[24],"by":[25,50],"simple":[26],"heuristics,":[27],"e.g.":[28],"concatenation":[29],"or":[30],"average":[31],"subset":[34],"layers,":[36],"with":[37],"consequent":[39],"need":[40],"for":[41],"calibrating":[42],"multiple":[43],"hyper-parameters":[44],"during":[45],"fine-tuning":[47],"phase.":[48],"Inspired":[49],"recent":[52],"literature,":[53],"we":[54,120],"propose":[55],"principled":[57],"approach":[58],"to":[59,128],"optimally":[60],"combine":[61],"model":[67,88],"via":[68],"Multiple":[69,98],"Kernel":[70,99],"Learning":[71,100],"strategies.":[72],"Broadly":[73],"speaking,":[74],"proposed":[76],"system":[77,123],"consists":[78],"two":[80],"elements.":[81],"The":[82,94],"former":[83],"canonical":[86],"fine-tuned":[89],"on":[90],"target":[92],"task.":[93],"latter":[95],"algorithm":[101],"that":[102],"extracts":[103],"combines":[105],"developed":[107],"in":[108],"layers":[111],"performs":[116],"predictions.":[117],"Most":[118],"important,":[119],"use":[121],"powerful":[126],"tool":[127],"inspect":[129],"information":[131],"encoded":[132],"into":[133],"network,":[136],"emphasizing":[137],"limits":[139],"state-of-the-art":[141],"models.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-09-27T00:00:00"}