{"id":"https://openalex.org/W3211620297","doi":"https://doi.org/10.18653/v1/2021.eval4nlp-1.3","title":"How Emotionally Stable is ALBERT? Testing Robustness with Stochastic Weight Averaging on a Sentiment Analysis Task","display_name":"How Emotionally Stable is ALBERT? Testing Robustness with Stochastic Weight Averaging on a Sentiment Analysis Task","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3211620297","doi":"https://doi.org/10.18653/v1/2021.eval4nlp-1.3","mag":"3211620297"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.eval4nlp-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.eval4nlp-1.3","pdf_url":"https://aclanthology.org/2021.eval4nlp-1.3.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2021.eval4nlp-1.3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021578462","display_name":"Urja Khurana","orcid":null},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Urja Khurana","raw_affiliation_strings":["Dept. of Language, Literature & Communication, Vrije Universiteit Amsterdam \u2666 Informatics Institute, University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Language, Literature & Communication, Vrije Universiteit Amsterdam \u2666 Informatics Institute, University of Amsterdam","institution_ids":["https://openalex.org/I865915315","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003054496","display_name":"Eric Nalisnick","orcid":"https://orcid.org/0009-0009-1188-612X"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Eric Nalisnick","raw_affiliation_strings":["Dept. of Language, Literature & Communication, Vrije Universiteit Amsterdam \u2666 Informatics Institute, University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Language, Literature & Communication, Vrije Universiteit Amsterdam \u2666 Informatics Institute, University of Amsterdam","institution_ids":["https://openalex.org/I865915315","https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074075557","display_name":"Antske Fokkens","orcid":"https://orcid.org/0000-0002-6628-6916"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Antske Fokkens","raw_affiliation_strings":["Dept. of Mathematics and Computerscience, Eindhoven University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Mathematics and Computerscience, Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074075557"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":0.8782,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77441851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9598000049591064,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9598000049591064,"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/T10320","display_name":"Neural Networks and Applications","score":0.9427000284194946,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9381999969482422,"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/robustness","display_name":"Robustness (evolution)","score":0.7153998613357544},{"id":"https://openalex.org/keywords/checklist","display_name":"Checklist","score":0.5837002992630005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5297338366508484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45023685693740845},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4295099973678589},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.42262911796569824},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.37031856179237366},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3629634976387024},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.36245667934417725},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36196890473365784},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.33465927839279175},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31330734491348267},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08310183882713318}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7153998613357544},{"id":"https://openalex.org/C2779356329","wikidata":"https://www.wikidata.org/wiki/Q922625","display_name":"Checklist","level":2,"score":0.5837002992630005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5297338366508484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45023685693740845},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4295099973678589},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.42262911796569824},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.37031856179237366},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3629634976387024},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.36245667934417725},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36196890473365784},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33465927839279175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31330734491348267},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08310183882713318},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2021.eval4nlp-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.eval4nlp-1.3","pdf_url":"https://aclanthology.org/2021.eval4nlp-1.3.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:research.vu.nl:openaire/771980b7-0503-4e95-96a5-b731fa160bed","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/771980b7-0503-4e95-96a5-b731fa160bed","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"},{"id":"pmh:oai:research.vu.nl:publications/771980b7-0503-4e95-96a5-b731fa160bed","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/771980b7-0503-4e95-96a5-b731fa160bed","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.eval4nlp-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.eval4nlp-1.3","pdf_url":"https://aclanthology.org/2021.eval4nlp-1.3.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3211620297.pdf","grobid_xml":"https://content.openalex.org/works/W3211620297.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1975879668","https://openalex.org/W2251939518","https://openalex.org/W2251964473","https://openalex.org/W2923014074","https://openalex.org/W2949858875","https://openalex.org/W2963173418","https://openalex.org/W2963310665","https://openalex.org/W2980282514","https://openalex.org/W2983368141","https://openalex.org/W2996428491","https://openalex.org/W3006963874","https://openalex.org/W3035507081","https://openalex.org/W3099624838","https://openalex.org/W3100511085","https://openalex.org/W3120706522","https://openalex.org/W3128630643","https://openalex.org/W3154151289","https://openalex.org/W3162754606","https://openalex.org/W3168830259","https://openalex.org/W3172318343","https://openalex.org/W3172794097","https://openalex.org/W3174057701","https://openalex.org/W3174617925","https://openalex.org/W3175987672","https://openalex.org/W3176683285","https://openalex.org/W3182543254","https://openalex.org/W4287110638"],"related_works":["https://openalex.org/W4234875088","https://openalex.org/W2013796470","https://openalex.org/W2420514274","https://openalex.org/W4362687946","https://openalex.org/W1971633942","https://openalex.org/W2902805979","https://openalex.org/W2145923542","https://openalex.org/W2987114614","https://openalex.org/W2808458916","https://openalex.org/W1987290620"],"abstract_inverted_index":{"Despite":[0],"their":[1,12,103],"success,":[2],"modern":[3],"language":[4],"models":[5,99],"are":[6],"fragile.":[7],"Even":[8],"small":[9],"changes":[10],"in":[11,34,95],"training":[13],"pipeline":[14],"can":[15],"lead":[16],"to":[17,108],"unexpected":[18],"results.":[19],"We":[20,59,77,88],"study":[21],"this":[22],"phenomenon":[23],"by":[24,80],"examining":[25],"the":[26,73,82,98],"robustness":[27],"of":[28,43],"ALBERT":[29],"(Lan":[30],"et":[31],"al.,":[32],"2020)":[33],"combination":[35],"with":[36,85],"Stochastic":[37],"Weight":[38],"Averaging":[39],"(SWA)-a":[40],"cheap":[41],"way":[42],"ensembling-on":[44],"a":[45],"sentiment":[46],"analysis":[47],"task":[48],"(SST-2).":[49],"In":[50],"particular,":[51],"we":[52],"analyze":[53],"SWA's":[54],"stability":[55,79],"via":[56],"CheckList":[57],"criteria":[58],"hypothesize":[60],"that":[61,90],"SWA":[62,91],"is":[63],"more":[64],"stable":[65],"because":[66],"it":[67],"ensembles":[68],"model":[69],"snapshots":[70],"taken":[71],"along":[72],"gradient":[74],"descent":[75],"trajectory.":[76],"quantify":[78],"comparing":[81],"models'":[83],"mistakes":[84],"Fleiss'":[86],"Kappa":[87],"find":[89],"reduces":[92],"error":[93],"rates":[94],"general;":[96],"yet":[97],"still":[100],"suffer":[101],"from":[102],"own":[104],"distinct":[105],"biases":[106],"(according":[107],"CheckList).":[109]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}
