{"id":"https://openalex.org/W4412888167","doi":"https://doi.org/10.18653/v1/2025.findings-acl.771","title":"DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation","display_name":"DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888167","doi":"https://doi.org/10.18653/v1/2025.findings-acl.771"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.771","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.771","pdf_url":"https://aclanthology.org/2025.findings-acl.771.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.771.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077286641","display_name":"Xinglin Lyu","orcid":"https://orcid.org/0000-0003-1971-6618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinglin Lyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669938","display_name":"Wei Tang","orcid":"https://orcid.org/0000-0002-9371-375X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032504077","display_name":"Yuang Li","orcid":"https://orcid.org/0000-0002-2244-0184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025545388","display_name":"Xiaofeng Zhao","orcid":"https://orcid.org/0000-0003-0316-7220"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofeng Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082364495","display_name":"Ming Zhu","orcid":"https://orcid.org/0000-0003-4474-1946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369260","display_name":"Junhui Li","orcid":"https://orcid.org/0000-0001-7829-6348"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junhui Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113627163","display_name":"Yunfei Lu","orcid":"https://orcid.org/0000-0001-5363-6836"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunfei Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671757","display_name":"M. Zhang","orcid":"https://orcid.org/0000-0001-8659-5727"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012613066","display_name":"Daimeng Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daimeng Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100671757","display_name":"M. Zhang","orcid":"https://orcid.org/0000-0001-8659-5727"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Zhang","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":"14910","last_page":"14924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9940000176429749,"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":0.9940000176429749,"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":0.9872000217437744,"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/T12031","display_name":"Speech and dialogue systems","score":0.9513999819755554,"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":0.7974817752838135},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.601826012134552},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5743677020072937},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5490975975990295},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5355162024497986},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4062395989894867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39581751823425293},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3720216155052185},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.04932066798210144}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7974817752838135},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.601826012134552},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5743677020072937},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5490975975990295},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5355162024497986},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4062395989894867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39581751823425293},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3720216155052185},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.04932066798210144},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.771","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.771","pdf_url":"https://aclanthology.org/2025.findings-acl.771.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.771","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.771","pdf_url":"https://aclanthology.org/2025.findings-acl.771.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":[],"awards":[{"id":"https://openalex.org/G5501069675","display_name":null,"funder_award_id":"62261160648","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5610393340","display_name":null,"funder_award_id":"62036004","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888167.pdf","grobid_xml":"https://content.openalex.org/works/W4412888167.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2775554247","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613","https://openalex.org/W123774389"],"abstract_inverted_index":{"Document-level":[0],"context":[1,30,61],"is":[2,62,98],"crucial":[3],"for":[4],"handling":[5],"discourse":[6,16,126],"challenges":[7,17],"in":[8,31,84,122,134],"text-to-text":[9],"documentlevel":[10],"machine":[11],"translation":[12,33],"(MT).Despite":[13],"the":[14,26,55,65,107,110],"increased":[15],"introduced":[18,99],"by":[19,50],"noise":[20],"from":[21,103],"automatic":[22],"speech":[23,32],"recognition":[24],"(ASR),":[25],"integration":[27],"of":[28,109],"document-level":[29,52,82],"(ST)":[34],"remains":[35],"insufficiently":[36],"explored.In":[37],"this":[38],"paper,":[39],"we":[40],"develop":[41],"DoCIA,":[42],"an":[43],"online":[44],"framework":[45],"that":[46,115],"enhances":[47],"ST":[48,56,120,136],"performance":[49],"incorporating":[51],"context.DoCIA":[53],"decomposes":[54],"pipeline":[57],"into":[58,64],"four":[59,129],"stages.Document-level":[60],"integrated":[63],"ASR":[66],"refinement,":[67,105],"MT,":[68],"and":[69,125],"MT":[70],"refinement":[71],"stages":[72],"through":[73],"auxiliary":[74],"LLM":[75],"(large":[76],"language":[77],"model)-based":[78],"modules.Furthermore,":[79],"DoCIA":[80,116],"leverages":[81],"information":[83],"a":[85,92],"multi-level":[86],"manner":[87],"while":[88],"minimizing":[89],"computational":[90],"overhead.Additionally,":[91],"simple":[93],"yet":[94],"effective":[95],"determination":[96],"mechanism":[97],"to":[100],"prevent":[101],"hallucinations":[102],"excessive":[104],"ensuring":[106],"reliability":[108],"final":[111],"results.Experimental":[112],"results":[113],"show":[114],"significantly":[117],"outperforms":[118],"traditional":[119],"baselines":[121],"both":[123],"sentence":[124],"metrics":[127],"across":[128],"LLMs,":[130],"demonstrating":[131],"its":[132],"effectiveness":[133],"improving":[135],"performance.":[137]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}