{"id":"https://openalex.org/W7127443908","doi":"https://doi.org/10.1145/3774904.3792262","title":"Hermes the Polyglot: A Unified Framework to Enhance Expressiveness for Multimodal Interlingual Subtitling","display_name":"Hermes the Polyglot: A Unified Framework to Enhance Expressiveness for Multimodal Interlingual Subtitling","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7127443908","doi":"https://doi.org/10.1145/3774904.3792262"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792262","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792262","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792262","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011051553","display_name":"Chaoqun Cui","orcid":"https://orcid.org/0009-0002-7487-7916"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chaoqun Cui","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of AI, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-7487-7916","affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of AI, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124965473","display_name":"Shijing Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijing Wang","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China and Hujing Digital Media &amp;#38; Entertainment Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-4937-8154","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China and Hujing Digital Media &amp;#38; Entertainment Group, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124892871","display_name":"Liangbin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144531","display_name":"Zeus Entertainment (China)","ror":"https://ror.org/05apznb79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangbin Huang","raw_affiliation_strings":["Hujing Digital Media &amp;#38; Entertainment Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-0336-7716","affiliations":[{"raw_affiliation_string":"Hujing Digital Media &amp;#38; Entertainment Group, Beijing, China","institution_ids":["https://openalex.org/I4210144531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124939447","display_name":"Qingqing Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153393","display_name":"Geely (China)","ror":"https://ror.org/0446d5v35","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210153393"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingqing Gu","raw_affiliation_strings":["Geely AI Lab, Ningbo, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0007-6872-8910","affiliations":[{"raw_affiliation_string":"Geely AI Lab, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I4210153393"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhaolong Huang","orcid":"https://orcid.org/0009-0006-5005-2601"},"institutions":[{"id":"https://openalex.org/I4210144531","display_name":"Zeus Entertainment (China)","ror":"https://ror.org/05apznb79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaolong Huang","raw_affiliation_strings":["Hujing Digital Media &amp;#38; Entertainment Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-5005-2601","affiliations":[{"raw_affiliation_string":"Hujing Digital Media &amp;#38; Entertainment Group, Beijing, China","institution_ids":["https://openalex.org/I4210144531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124926693","display_name":"Xiao Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144531","display_name":"Zeus Entertainment (China)","ror":"https://ror.org/05apznb79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Zeng","raw_affiliation_strings":["Hujing Digital Media &amp;#38; Entertainment Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-0635-1358","affiliations":[{"raw_affiliation_string":"Hujing Digital Media &amp;#38; Entertainment Group, Beijing, China","institution_ids":["https://openalex.org/I4210144531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122346800","display_name":"Wenji Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenji Mao","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of AI, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2323-5091","affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of AI, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5011051553"],"corresponding_institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19955047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7068","last_page":"7079"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.5180000066757202,"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"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.5180000066757202,"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/T10759","display_name":"Translation Studies and Practices","score":0.13030000030994415,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10350000113248825,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/terminology","display_name":"Terminology","score":0.6366000175476074},{"id":"https://openalex.org/keywords/subtitle","display_name":"Subtitle","score":0.5206000208854675},{"id":"https://openalex.org/keywords/pronoun","display_name":"Pronoun","score":0.4106000065803528},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.38670000433921814},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3626999855041504},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.3255000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781000018119812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6470000147819519},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.6366000175476074},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5629000067710876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5576000213623047},{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C2778551981","wikidata":"https://www.wikidata.org/wiki/Q36224","display_name":"Pronoun","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.26460000872612},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3774904.3792262","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792262","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.00597","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.00597","pdf_url":"https://arxiv.org/pdf/2602.00597","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792262","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792262","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.826542317867279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Interlingual":[0],"subtitling,":[1,51],"which":[2,86],"translates":[3],"subtitles":[4],"of":[5,37,43],"visual":[6],"media":[7],"into":[8],"a":[9],"target":[10],"language,":[11],"is":[12],"essential":[13],"for":[14],"entertainment":[15],"localization":[16],"but":[17],"has":[18],"not":[19],"yet":[20],"been":[21],"explored":[22],"in":[23,49,109],"machine":[24,38],"translation.":[25],"Although":[26],"Large":[27],"Language":[28],"Models":[29],"(LLMs)":[30],"have":[31],"significantly":[32],"advanced":[33],"the":[34,40,89],"general":[35],"capabilities":[36],"translation,":[39,59],"distinctive":[41],"characteristics":[42],"subtitle":[44],"texts":[45],"pose":[46],"persistent":[47],"challenges":[48],"interlingual":[50,110],"particularly":[52],"regarding":[53],"semantic":[54],"coherence,":[55],"pronoun":[56],"and":[57,60,83,100],"terminology":[58],"translation":[61],"expressiveness.":[62],"To":[63],"address":[64],"these":[65],"issues,":[66],"we":[67],"present":[68],"Hermes,":[69],"an":[70],"LLM-based":[71],"automated":[72],"subtitling":[73],"framework.":[74],"Hermes":[75,95],"integrates":[76],"three":[77],"modules:":[78],"Speaker":[79],"Diarization,":[80],"Terminology":[81],"Identification,":[82],"Expressiveness":[84],"Enhancement,":[85],"effectively":[87],"tackle":[88],"above":[90],"challenges.":[91],"Experiments":[92],"demonstrate":[93],"that":[94],"achieves":[96],"state-of-the-art":[97],"diarization":[98],"performance":[99],"generates":[101],"expressive,":[102],"contextually":[103],"coherent":[104],"translations,":[105],"thereby":[106],"advancing":[107],"research":[108],"subtitling.":[111]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-02-04T00:00:00"}
