{"id":"https://openalex.org/W4411630062","doi":"https://doi.org/10.18653/v1/2024.eacl-long.157","title":"Should I try multiple optimizers when fine-tuning a pre-trained Transformer for NLP tasks? Should I tune their hyperparameters?","display_name":"Should I try multiple optimizers when fine-tuning a pre-trained Transformer for NLP tasks? Should I tune their hyperparameters?","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4411630062","doi":"https://doi.org/10.18653/v1/2024.eacl-long.157"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.eacl-long.157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.157","pdf_url":"https://aclanthology.org/2024.eacl-long.157.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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.eacl-long.157.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093925777","display_name":"Nefeli Gkouti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nefeli Gkouti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016618602","display_name":"Prodromos Malakasiotis","orcid":"https://orcid.org/0009-0008-0055-5598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prodromos Malakasiotis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044841359","display_name":"Stavros Toumpis","orcid":"https://orcid.org/0000-0003-0438-397X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stavros Toumpis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069270736","display_name":"Ion Androutsopoulos","orcid":"https://orcid.org/0009-0000-2969-0509"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ion Androutsopoulos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69532477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2555","last_page":"2574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.984000027179718,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.984000027179718,"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/T10028","display_name":"Topic Modeling","score":0.9807999730110168,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.925000011920929,"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/hyperparameter","display_name":"Hyperparameter","score":0.9244613647460938},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.750346302986145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7419476509094238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6116732954978943},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44007983803749084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40331393480300903},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3546537160873413},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32461434602737427},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1287187933921814},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12832805514335632},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06647789478302002}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.9244613647460938},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.750346302986145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419476509094238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6116732954978943},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44007983803749084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40331393480300903},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3546537160873413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32461434602737427},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1287187933921814},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12832805514335632},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06647789478302002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.eacl-long.157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.157","pdf_url":"https://aclanthology.org/2024.eacl-long.157.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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.eacl-long.157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.157","pdf_url":"https://aclanthology.org/2024.eacl-long.157.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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411630062.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W2602382373","https://openalex.org/W3003615511","https://openalex.org/W4285827128","https://openalex.org/W3198113463","https://openalex.org/W2787698406","https://openalex.org/W2963844355","https://openalex.org/W4361251046","https://openalex.org/W98577079"],"abstract_inverted_index":{"Nefeli":[0],"Gkouti,":[1],"Prodromos":[2],"Malakasiotis,":[3],"Stavros":[4],"Toumpis,":[5],"Ion":[6],"Androutsopoulos.":[7],"Proceedings":[8],"of":[9,13,17],"the":[10,14,18],"18th":[11],"Conference":[12],"European":[15],"Chapter":[16],"Association":[19],"for":[20],"Computational":[21],"Linguistics":[22],"(Volume":[23],"1:":[24],"Long":[25],"Papers).":[26],"2024.":[27]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
