{"id":"https://openalex.org/W4402670910","doi":"https://doi.org/10.18653/v1/2024.findings-acl.560","title":"Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning","display_name":"Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402670910","doi":"https://doi.org/10.18653/v1/2024.findings-acl.560"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-acl.560","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-acl.560","pdf_url":"https://aclanthology.org/2024.findings-acl.560.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":"Findings of the Association for Computational Linguistics ACL 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-acl.560.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057280613","display_name":"Everlyn Asiko Chimoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Everlyn Chimoto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024885077","display_name":"Jay Gala","orcid":"https://orcid.org/0009-0001-2894-9897"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jay Gala","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045507345","display_name":"Orevaoghene Ahia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Orevaoghene Ahia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048307591","display_name":"Julia Kreutzer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julia Kreutzer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079541342","display_name":"Bruce A. Bassett","orcid":"https://orcid.org/0000-0001-7700-1069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bruce Bassett","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078850040","display_name":"Sara Hooker","orcid":"https://orcid.org/0000-0002-0190-6459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sara Hooker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9407","last_page":"9426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11875","display_name":"Statistics Education and Methodologies","score":0.7609000205993652,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11875","display_name":"Statistics Education and Methodologies","score":0.7609000205993652,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7890712022781372},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7573256492614746},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7207922339439392},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5934325456619263},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5748488903045654},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.542770504951477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.538844108581543},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4522554874420166},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32330209016799927},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10604649782180786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890712022781372},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7573256492614746},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7207922339439392},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5934325456619263},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5748488903045654},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.542770504951477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.538844108581543},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4522554874420166},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32330209016799927},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10604649782180786},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-acl.560","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-acl.560","pdf_url":"https://aclanthology.org/2024.findings-acl.560.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":"Findings of the Association for Computational Linguistics ACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-acl.560","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-acl.560","pdf_url":"https://aclanthology.org/2024.findings-acl.560.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":"Findings of the Association for Computational Linguistics ACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402670910.pdf","grobid_xml":"https://content.openalex.org/works/W4402670910.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W2373300491","https://openalex.org/W4394050964","https://openalex.org/W2551249631","https://openalex.org/W4285322112","https://openalex.org/W4292794239"],"abstract_inverted_index":{"Neural":[0],"Machine":[1],"Translation":[2],"models":[3],"are":[4],"extremely":[5],"data":[6,11,25,49,67,76,124],"and":[7,18,82,101,129,138],"compute-hungry.However,":[8],"not":[9],"all":[10],"points":[12,26,68,125],"contribute":[13],"equally":[14],"to":[15,21,62,98,109,117,134],"model":[16,41,59,70],"training":[17,60,120],"generalization.Data":[19],"pruning":[20,50,77,115],"remove":[22],"the":[23,28,33,64,88,111,123],"low-value":[24],"has":[27],"benefit":[29],"of":[30,119],"drastically":[31],"reducing":[32],"compute":[34],"budget":[35],"without":[36],"a":[37,47],"significant":[38],"drop":[39],"in":[40],"performance.In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"new":[48],"technique:":[51],"Checkpoints":[52],"Across":[53],"Time":[54],"(CAT),":[55],"that":[56,85,126,131],"leverages":[57],"early":[58],"dynamics":[61],"identify":[63],"most":[65],"relevant":[66],"for":[69],"performance.We":[71],"benchmark":[72],"CAT":[73,86,105,127],"against":[74],"several":[75],"techniques":[78],"including":[79],"COMET-QE,":[80],"LASER":[81],"LaBSE.We":[83],"find":[84,130],"outperforms":[87],"benchmarks":[89],"on":[90,93],"Indo-European":[91],"languages":[92],"multiple":[94],"test":[95],"sets.When":[96],"applied":[97],"English-German,":[99],"English-French":[100],"English-Swahili":[102],"translation":[103],"tasks,":[104],"achieves":[106],"comparable":[107],"performance":[108],"using":[110],"full":[112],"dataset,":[113],"while":[114],"up":[116],"50%":[118],"data.We":[121],"inspect":[122],"selects":[128],"it":[132],"tends":[133],"favor":[135],"longer":[136],"sentences":[137,139],"with":[140],"unique":[141],"or":[142],"rare":[143],"words.":[144]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}