{"id":"https://openalex.org/W4416036057","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.104","title":"Train a Unified Multimodal Data Quality Classifier with Synthetic Data","display_name":"Train a Unified Multimodal Data Quality Classifier with Synthetic Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036057","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.104"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.104","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.104","pdf_url":"https://aclanthology.org/2025.findings-emnlp.104.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.104.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062260595","display_name":"Weizhi Wang","orcid":"https://orcid.org/0000-0002-7310-4068"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weizhi Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050956010","display_name":"Rongmei Lin","orcid":"https://orcid.org/0000-0002-3325-5590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongmei Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685009","display_name":"Shiyang Li","orcid":"https://orcid.org/0000-0002-8883-0759"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056881273","display_name":"Colin Lockard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Colin Lockard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014228532","display_name":"Ritesh Sarkhel","orcid":"https://orcid.org/0000-0002-9116-1517"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ritesh Sarkhel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116225215","display_name":"Sanket Lokegaonkar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanket Lokegaonkar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039500313","display_name":"Jingbo Shang","orcid":"https://orcid.org/0000-0002-7249-4404"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingbo Shang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xifeng Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xifeng Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089887413","display_name":"Nasser Zalmout","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nasser Zalmout","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066365471","display_name":"Xian Li","orcid":"https://orcid.org/0000-0003-0108-7665"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xian Li","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":"1972","last_page":"1986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.18160000443458557,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.18160000443458557,"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":0.156700000166893,"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/T11719","display_name":"Data Quality and Management","score":0.1551000028848648,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5622000098228455},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5314000248908997},{"id":"https://openalex.org/keywords/data-association","display_name":"Data association","score":0.43160000443458557},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.42579999566078186},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.38530001044273376},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3549000024795532},{"id":"https://openalex.org/keywords/real-world-data","display_name":"Real world data","score":0.3070000112056732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6126000285148621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6000000238418579},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5622000098228455},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C2983325608","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Data association","level":3,"score":0.43160000443458557},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.42579999566078186},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36809998750686646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3167000114917755},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.104","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.104","pdf_url":"https://aclanthology.org/2025.findings-emnlp.104.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.104","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.104","pdf_url":"https://aclanthology.org/2025.findings-emnlp.104.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036057.pdf","grobid_xml":"https://content.openalex.org/works/W4416036057.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Weizhi":[0],"Wang,":[1],"Rongmei":[2],"Lin,":[3],"Shiyang":[4],"Li,":[5],"Colin":[6],"Lockard,":[7],"Ritesh":[8],"Sarkhel,":[9],"Sanket":[10],"Lokegaonkar,":[11],"Jingbo":[12],"Shang,":[13],"Xifeng":[14],"Yan,":[15],"Nasser":[16],"Zalmout,":[17],"Xian":[18],"Li.":[19],"Findings":[20],"of":[21],"the":[22],"Association":[23],"for":[24],"Computational":[25],"Linguistics:":[26],"EMNLP":[27],"2025.":[28,29]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}