{"id":"https://openalex.org/W4412888456","doi":"https://doi.org/10.18653/v1/2025.findings-acl.433","title":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data","display_name":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888456","doi":"https://doi.org/10.18653/v1/2025.findings-acl.433"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.433","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.433","pdf_url":"https://aclanthology.org/2025.findings-acl.433.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 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-acl.433.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100767773","display_name":"Haonan Chen","orcid":"https://orcid.org/0000-0002-9642-972X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haonan Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325702","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0003-4664-7136"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100680993","display_name":"Nan Yang","orcid":"https://orcid.org/0000-0002-9373-5289"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007186741","display_name":"Yutao Zhu","orcid":"https://orcid.org/0000-0002-9432-3251"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutao Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036094777","display_name":"Ziliang Zhao","orcid":"https://orcid.org/0000-0001-8169-0143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziliang Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Furu Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010558184","display_name":"Zhicheng Dou","orcid":"https://orcid.org/0000-0002-9781-948X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhicheng Dou","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":6.4958,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96831695,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8254","last_page":"8275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.944599986076355,"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/T12031","display_name":"Speech and dialogue systems","score":0.944599986076355,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9251000285148621,"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":0.7307060956954956},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5534449219703674},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4552539587020874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43221715092658997},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42774638533592224},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08736583590507507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307060956954956},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5534449219703674},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4552539587020874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43221715092658997},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42774638533592224},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08736583590507507},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.433","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.433","pdf_url":"https://aclanthology.org/2025.findings-acl.433.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.433","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.433","pdf_url":"https://aclanthology.org/2025.findings-acl.433.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4399999976158142,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1899978318","display_name":null,"funder_award_id":"L233008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G228125052","display_name":null,"funder_award_id":"62272467","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888456.pdf","grobid_xml":"https://content.openalex.org/works/W4412888456.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multimodal":[0],"embedding":[1,33],"models":[2,194],"have":[3,36],"gained":[4],"significant":[5],"attention":[6],"for":[7,60],"their":[8],"ability":[9],"to":[10,40,80,102],"map":[11],"data":[12,30,38,49,71,98],"from":[13],"different":[14,88],"modalities,":[15,76],"such":[16],"as":[17],"text":[18],"and":[19,75,122,142,149,156,161,183,193],"images,":[20],"into":[21],"a":[22,51,115,128,133,137,166],"unified":[23],"representation":[24],"space.However,":[25],"the":[26,45,69,96,180,188],"limited":[27],"labeled":[28,162],"multimodal":[29,63,138,167],"often":[31],"hinders":[32],"performance.Recent":[34],"approaches":[35],"leveraged":[37],"synthesis":[39],"address":[41],"this":[42,54],"problem,":[43],"yet":[44],"quality":[46],"of":[47,118,136],"synthetic":[48,62,97,160],"remains":[50],"critical":[52],"bottleneck.In":[53],"work,":[55],"we":[56,109,164],"identify":[57],"three":[58],"criteria":[59],"high-quality":[61,159],"data.First,":[64],"broad":[65],"scope":[66],"ensures":[67,94],"that":[68,95,174],"generated":[70,126],"covers":[72],"diverse":[73],"tasks":[74],"making":[77],"it":[78],"applicable":[79],"various":[81],"downstream":[82],"scenarios.Second,":[83],"robust":[84],"cross-modal":[85],"alignment":[86],"makes":[87],"modalities":[89],"semantically":[90],"consistent.Third,":[91],"high":[92],"fidelity":[93,153],"maintains":[99],"realistic":[100],"details":[101],"enhance":[103],"its":[104],"reliability.Guided":[105],"by":[106],"these":[107,158],"principles,":[108],"synthesize":[110],"datasets":[111],"that:":[112],"(1)":[113],"cover":[114],"wide":[116],"range":[117],"tasks,":[119],"modality":[120],"combinations,":[121],"languages,":[123],"(2)":[124],"are":[125,195],"via":[127],"deep":[129],"thinking":[130],"process":[131],"within":[132],"single":[134],"pass":[135],"large":[139],"language":[140],"model,":[141],"(3)":[143],"incorporate":[144],"real-world":[145],"images":[146],"with":[147],"accurate":[148],"relevant":[150],"texts,":[151],"ensuring":[152],"through":[154],"selfevaluation":[155],"refinement.Leveraging":[157],"datasets,":[163,192],"train":[165],"multilingual":[168,185],"E5":[169],"model":[170],"mmE5.Extensive":[171],"experiments":[172],"demonstrate":[173],"mmE5":[175],"achieves":[176],"state-of-the-art":[177],"performance":[178,186],"on":[179,187],"MMEB":[181],"Benchmark":[182],"superior":[184],"XTD":[189],"benchmark.Our":[190],"codes,":[191],"released":[196],"in":[197],"https://github.com/haon-chen/mmE5.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}