{"id":"https://openalex.org/W7134175295","doi":"https://doi.org/10.1109/bigdata66926.2025.11402145","title":"Improving Translation Quality by Selecting Better Data for LLM Fine-Tuning: A Comparative Analysis","display_name":"Improving Translation Quality by Selecting Better Data for LLM Fine-Tuning: A Comparative Analysis","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7134175295","doi":"https://doi.org/10.1109/bigdata66926.2025.11402145"},"language":null,"primary_location":{"id":"doi:10.1109/bigdata66926.2025.11402145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11402145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128343450","display_name":"Felipe Ribeiro Fujita de Mello","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Felipe Ribeiro Fujita de Mello","raw_affiliation_strings":["Ritsumeikan University,Osaka,Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Osaka,Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075886507","display_name":"Hideyuki Takada","orcid":"https://orcid.org/0000-0002-6349-8155"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideyuki Takada","raw_affiliation_strings":["Ritsumeikan University,Osaka,Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Osaka,Japan","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5128343450"],"corresponding_institution_ids":["https://openalex.org/I135768898"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88616242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5490","last_page":"5499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6779000163078308,"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":0.6779000163078308,"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/T10759","display_name":"Translation Studies and Practices","score":0.01759999990463257,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.009100000374019146,"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/quality","display_name":"Quality (philosophy)","score":0.58160001039505},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.366100013256073},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.3628999888896942},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3100000023841858},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27649998664855957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6259999871253967},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.58160001039505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4844000041484833},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.366100013256073},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3628999888896942},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3433000147342682},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2669999897480011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata66926.2025.11402145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11402145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4648800492286682}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2773493195","https://openalex.org/W4404783397","https://openalex.org/W4412888209","https://openalex.org/W4416033464","https://openalex.org/W7126414507","https://openalex.org/W7126431584"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-09T07:06:17.341095","created_date":"2026-03-09T00:00:00"}
