{"id":"https://openalex.org/W4412945403","doi":"https://doi.org/10.18653/v1/2025.acl-long.533","title":"Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models","display_name":"Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945403","doi":"https://doi.org/10.18653/v1/2025.acl-long.533"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.533","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.533","pdf_url":"https://aclanthology.org/2025.acl-long.533.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 63rd Annual Meeting 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/2025.acl-long.533.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054159373","display_name":"Xinlin Zhuang","orcid":"https://orcid.org/0009-0006-1822-8224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinlin Zhuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101707851","display_name":"Jiahui Peng","orcid":"https://orcid.org/0000-0002-4936-7626"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahui Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077938328","display_name":"Ren Ma","orcid":"https://orcid.org/0000-0002-6958-1443"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113157111","display_name":"Yinfan Wang","orcid":"https://orcid.org/0000-0002-3943-8515"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinfan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102781208","display_name":"Tianyi Bai","orcid":"https://orcid.org/0009-0009-5057-7100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyi Bai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085530044","display_name":"Xingjian Wei","orcid":"https://orcid.org/0000-0002-3217-6823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingjian Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111396982","display_name":"Qiu Jiantao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu Jiantao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102010202","display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0002-6142-120X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101444861","display_name":"Ying Qian","orcid":"https://orcid.org/0000-0003-4961-5842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101615091","display_name":"Conghui He","orcid":"https://orcid.org/0000-0001-8697-695X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Conghui He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87865649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10856","last_page":"10896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9793999791145325,"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/T10028","display_name":"Topic Modeling","score":0.9793999791145325,"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":0.9671000242233276,"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/computer-science","display_name":"Computer science","score":0.7663252353668213},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5906567573547363},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4652031362056732},{"id":"https://openalex.org/keywords/inter-rater-reliability","display_name":"Inter-rater reliability","score":0.44348862767219543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4172501564025879},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4141750931739807},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3491072654724121},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33012884855270386},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2067970633506775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0969947874546051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663252353668213},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5906567573547363},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4652031362056732},{"id":"https://openalex.org/C61863361","wikidata":"https://www.wikidata.org/wiki/Q470749","display_name":"Inter-rater reliability","level":3,"score":0.44348862767219543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4172501564025879},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4141750931739807},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3491072654724121},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33012884855270386},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2067970633506775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0969947874546051},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C83849319","wikidata":"https://www.wikidata.org/wiki/Q7295720","display_name":"Rating scale","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.533","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.533","pdf_url":"https://aclanthology.org/2025.acl-long.533.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.533","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.533","pdf_url":"https://aclanthology.org/2025.acl-long.533.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 63rd Annual Meeting 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/W4412945403.pdf","grobid_xml":"https://content.openalex.org/works/W4412945403.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1967059694","https://openalex.org/W1997597399","https://openalex.org/W3124297919","https://openalex.org/W2167816954","https://openalex.org/W2365664655","https://openalex.org/W2073642463","https://openalex.org/W2923540558","https://openalex.org/W230091440","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Xinlin":[0],"Zhuang,":[1],"Jiahui":[2],"Peng,":[3],"Ren":[4],"Ma,":[5],"Yinfan":[6],"Wang,":[7],"Tianyi":[8],"Bai,":[9],"Xingjian":[10],"Wei,":[11],"Qiu":[12],"Jiantao,":[13],"Chi":[14],"Zhang,":[15],"Ying":[16],"Qian,":[17],"Conghui":[18],"He.":[19],"Proceedings":[20],"of":[21,26],"the":[22,27],"63rd":[23],"Annual":[24],"Meeting":[25],"Association":[28],"for":[29],"Computational":[30],"Linguistics":[31],"(Volume":[32],"1:":[33],"Long":[34],"Papers).":[35],"2025.":[36]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}