{"id":"https://openalex.org/W4412888621","doi":"https://doi.org/10.18653/v1/2025.findings-acl.372","title":"A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration","display_name":"A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888621","doi":"https://doi.org/10.18653/v1/2025.findings-acl.372"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.372","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.372","pdf_url":"https://aclanthology.org/2025.findings-acl.372.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.372.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115593821","display_name":"Zhiyang Zhang","orcid":"https://orcid.org/0009-0004-4057-7098"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090919681","display_name":"Yaping Zhang","orcid":"https://orcid.org/0000-0001-6892-905X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaping Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016559205","display_name":"Yupu Liang","orcid":"https://orcid.org/0000-0003-4074-463X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yupu Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438517","display_name":"Zhiyuan Chen","orcid":"https://orcid.org/0000-0002-9828-5272"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101710116","display_name":"Xiang Lu","orcid":"https://orcid.org/0009-0001-7914-7640"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101961736","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0002-3126-4944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101815945","display_name":"Zhou Yu","orcid":"https://orcid.org/0000-0002-1524-5890"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015785439","display_name":"Chengqing Zong","orcid":"https://orcid.org/0000-0002-9864-3818"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengqing Zong","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":"7138","last_page":"7149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9926999807357788,"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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9926999807357788,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9595999717712402,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9257000088691711,"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/computer-science","display_name":"Computer science","score":0.8352890610694885},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.710585355758667},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5274938344955444},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4404154419898987},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33774855732917786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8352890610694885},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.710585355758667},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5274938344955444},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4404154419898987},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33774855732917786},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.372","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.372","pdf_url":"https://aclanthology.org/2025.findings-acl.372.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.372","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.372","pdf_url":"https://aclanthology.org/2025.findings-acl.372.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/G1883487206","display_name":null,"funder_award_id":"62336008","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888621.pdf","grobid_xml":"https://content.openalex.org/works/W4412888621.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3001245047","https://openalex.org/W1873153460","https://openalex.org/W850316024","https://openalex.org/W2170059263","https://openalex.org/W2044231962","https://openalex.org/W2945915803","https://openalex.org/W2969770061","https://openalex.org/W301348785","https://openalex.org/W2117230983","https://openalex.org/W4390861283"],"abstract_inverted_index":{"Document":[0,22],"Image":[1],"Translation":[2],"(DIT),":[3],"which":[4],"aims":[5],"at":[6],"translating":[7],"documents":[8],"in":[9,21,68,122,128],"images":[10],"from":[11],"source":[12,94],"language":[13],"to":[14,106,117],"the":[15,47,80,89,101,119],"target,":[16],"plays":[17],"an":[18],"important":[19],"role":[20],"Intelligence.It":[23],"requires":[24],"a":[25,32,73,84],"comprehensive":[26],"understanding":[27],"of":[28,88],"document":[29,63,147],"multi-modalities":[30],"and":[31],"focused":[33],"concentration":[34,53],"on":[35,46,54,132],"relevant":[36,93,103],"textual":[37,104],"regions":[38,56,105],"during":[39],"translation.However,":[40],"most":[41,102],"existing":[42],"methods":[43],"usually":[44],"rely":[45],"vanilla":[48],"encoder-decoder":[49],"paradigm,":[50],"severely":[51],"losing":[52],"key":[55],"that":[57],"are":[58],"especially":[59],"crucial":[60],"for":[61],"complexlayout":[62],"translation.To":[64],"tackle":[65],"this":[66,69],"issue,":[67],"paper,":[70],"we":[71],"propose":[72],"new":[74],"Query-Response":[75],"DIT":[76,81],"framework":[77],"(QRDIT).QRDIT":[78],"reformulates":[79],"task":[82],"into":[83],"parallel":[85],"response/translation":[86],"process":[87],"multiple":[90],"queries":[91],"(i.e.,":[92],"texts),":[95],"explicitly":[96],"centralizing":[97],"its":[98,136],"focus":[99],"toward":[100,125,144],"ensure":[107],"translation":[108,130,141],"accuracy.A":[109],"novel":[110],"dynamic":[111],"aggregation":[112],"mechanism":[113],"is":[114],"also":[115],"designed":[116],"enhance":[118],"text":[120],"semantics":[121],"query":[123],"features":[124],"translation.Extensive":[126],"experiments":[127],"four":[129],"directions":[131],"three":[133],"benchmarks":[134],"demonstrate":[135],"state-of-theart":[137],"performance,":[138],"showing":[139],"significant":[140],"quality":[142],"improvements":[143],"whole-page":[145],"complex-layout":[146],"images.":[148]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
