{"id":"https://openalex.org/W4411630251","doi":"https://doi.org/10.18653/v1/2024.eacl-long.40","title":"Quantifying the Hyperparameter Sensitivity of Neural Networks for Character-level Sequence-to-Sequence Tasks","display_name":"Quantifying the Hyperparameter Sensitivity of Neural Networks for Character-level Sequence-to-Sequence Tasks","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4411630251","doi":"https://doi.org/10.18653/v1/2024.eacl-long.40"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.eacl-long.40","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.40","pdf_url":"https://aclanthology.org/2024.eacl-long.40.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.40.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012580224","display_name":"Adam Wiemerslage","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Wiemerslage","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011757745","display_name":"Kyle Gorman","orcid":"https://orcid.org/0000-0002-4233-6595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyle Gorman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5093081493","display_name":"Katharina von der Wense","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katharina von der Wense","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2219,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84072144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"674","last_page":"689"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9578999876976013,"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/T10320","display_name":"Neural Networks and Applications","score":0.9578999876976013,"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":0.8524799346923828},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7262892723083496},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6782411932945251},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.6438024640083313},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5862534046173096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5512335300445557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5229693055152893},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40180906653404236},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35496437549591064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18611237406730652},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10084563493728638},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.06373429298400879}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8524799346923828},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7262892723083496},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6782411932945251},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.6438024640083313},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5862534046173096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5512335300445557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5229693055152893},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40180906653404236},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35496437549591064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18611237406730652},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10084563493728638},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.06373429298400879},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.eacl-long.40","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.40","pdf_url":"https://aclanthology.org/2024.eacl-long.40.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.40","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.40","pdf_url":"https://aclanthology.org/2024.eacl-long.40.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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411630251.pdf","grobid_xml":"https://content.openalex.org/works/W4411630251.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W2140186469","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W2775233965","https://openalex.org/W4318559728","https://openalex.org/W4360995913","https://openalex.org/W4312193868","https://openalex.org/W4308165509"],"abstract_inverted_index":{"Hyperparameter":[0],"tuning,":[1],"the":[2,13,91],"process":[3],"of":[4,32,102],"searching":[5],"for":[6],"suitable":[7],"hyperparameters,":[8],"becomes":[9],"more":[10,63,95,112],"difficult":[11],"as":[12],"computing":[14],"resources":[15],"required":[16],"to":[17,22,26,39,55,65,76,97,100,114],"train":[18],"neural":[19],"networks":[20],"continue":[21],"grow.This":[23],"topic":[24],"continues":[25],"receive":[27],"little":[28],"attention":[29],"and":[30,48,70,87],"discussion-much":[31],"it":[33,110],"hearsaydespite":[34],"its":[35],"obvious":[36],"importance.We":[37],"attempt":[38],"formalize":[40],"hyperparameter":[41,66],"sensitivity":[42,47],"using":[43],"two":[44,57,82],"metrics:":[45],"similarity-based":[46],"performance-based":[49],"sensitivity.We":[50],"then":[51],"use":[52],"these":[53],"metrics":[54],"quantify":[56],"such":[58],"claims:":[59],"(1)":[60],"transformers":[61,72],"are":[62,73],"sensitive":[64,75,96,113],"choices":[67],"than":[68],"LSTMs":[69],"(2)":[71],"particularly":[74],"batch":[77,115],"size.We":[78],"conduct":[79],"experiments":[80],"on":[81],"different":[83],"characterlevel":[84],"sequence-to-sequence":[85],"tasks":[86],"find":[88,108],"that,":[89],"indeed,":[90],"transformer":[92],"is":[93,111],"slightly":[94],"hyperparameters":[98],"according":[99],"both":[101],"our":[103],"metrics.However,":[104],"we":[105],"do":[106],"not":[107],"that":[109],"size":[116],"in":[117],"particular.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}