{"id":"https://openalex.org/W7140115564","doi":"https://doi.org/10.18653/v1/2026.eacl-long.271","title":"Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning","display_name":"Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140115564","doi":"https://doi.org/10.18653/v1/2026.eacl-long.271"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.271","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.271","pdf_url":"https://aclanthology.org/2026.eacl-long.271.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.271.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Amr Mohamed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amr Mohamed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hadi Abdine","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hadi Abdine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Guokan Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guokan Shang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Michalis Vazirgiannis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michalis Vazirgiannis","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":21.2894,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98164698,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5776","last_page":"5794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.3659000098705292,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.3659000098705292,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.10970000177621841,"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/T12884","display_name":"Educational Assessment and Pedagogy","score":0.028599999845027924,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42820000648498535},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.3896999955177307},{"id":"https://openalex.org/keywords/language-acquisition","display_name":"Language acquisition","score":0.3467999994754791},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.2703999876976013},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.2639999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.593500018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44940000772476196},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4235999882221222},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3366999924182892},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31200000643730164},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C37228920","wikidata":"https://www.wikidata.org/wiki/Q1307600","display_name":"Experiential learning","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.271","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.271","pdf_url":"https://aclanthology.org/2026.eacl-long.271.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 19th 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/v1/2026.eacl-long.271","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.271","pdf_url":"https://aclanthology.org/2026.eacl-long.271.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5401732325553894}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140115564.pdf","grobid_xml":"https://content.openalex.org/works/W7140115564.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Yang":[0],"Zhang,":[1],"Amr":[2],"Mohamed,":[3],"Hadi":[4],"Abdine,":[5],"Guokan":[6],"Shang,":[7],"Michalis":[8],"Vazirgiannis.":[9],"Proceedings":[10],"of":[11,15,19],"the":[12,16,20],"19th":[13],"Conference":[14],"European":[17],"Chapter":[18],"Association":[21],"for":[22],"Computational":[23],"Linguistics":[24],"(Volume":[25],"1:":[26],"Long":[27],"Papers).":[28],"2026.":[29]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-02T00:00:00"}
