{"id":"https://openalex.org/W4416033889","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.782","title":"SubDocTrans: Enhancing Document-level Machine Translation with Plug-and-play Multi-granularity Knowledge Augmentation","display_name":"SubDocTrans: Enhancing Document-level Machine Translation with Plug-and-play Multi-granularity Knowledge Augmentation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033889","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.782"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.782","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.782","pdf_url":"https://aclanthology.org/2025.findings-emnlp.782.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.782.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109686195","display_name":"Hanghai Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanghai Hong","raw_affiliation_strings":["School of Informatics , Xiamen University Research Center of Star-XLAB , Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics , Xiamen University Research Center of Star-XLAB , Xiamen University","institution_ids":["https://openalex.org/I191208505","https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027667056","display_name":"Yibo Xie","orcid":"https://orcid.org/0009-0008-3651-654X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Xie","raw_affiliation_strings":["School of Informatics , Xiamen University Research Center of Star-XLAB , Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics , Xiamen University Research Center of Star-XLAB , Xiamen University","institution_ids":["https://openalex.org/I191208505","https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102495507","display_name":"Jiawei Zheng","orcid":"https://orcid.org/0009-0003-9643-3643"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Zheng","raw_affiliation_strings":["School of Informatics , Xiamen University Research Center of Star-XLAB , Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics , Xiamen University Research Center of Star-XLAB , Xiamen University","institution_ids":["https://openalex.org/I191208505","https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100456913","display_name":"Xiaoli Wang","orcid":"https://orcid.org/0000-0002-8677-9080"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoli Wang","raw_affiliation_strings":["School of Informatics , Xiamen University Research Center of Star-XLAB , Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics , Xiamen University Research Center of Star-XLAB , Xiamen University","institution_ids":["https://openalex.org/I191208505","https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"14490","last_page":"14506"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9584000110626221,"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":0.9584000110626221,"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/T10028","display_name":"Topic Modeling","score":0.012799999676644802,"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/T13629","display_name":"Text Readability and Simplification","score":0.004699999932199717,"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/machine-translation","display_name":"Machine translation","score":0.4117000102996826},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.33180001378059387},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.2924000024795532},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26820001006126404},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.26750001311302185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6342999935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134000182151794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4350000023841858},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.33180001378059387},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23800000548362732}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.782","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.782","pdf_url":"https://aclanthology.org/2025.findings-emnlp.782.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.782","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.782","pdf_url":"https://aclanthology.org/2025.findings-emnlp.782.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":[{"id":"https://openalex.org/F4320325434","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033889.pdf","grobid_xml":"https://content.openalex.org/works/W4416033889.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"recently":[5],"achieved":[6],"remarkable":[7],"progress":[8],"in":[9,23,120,145],"sentence-level":[10],"machine":[11,17],"translation,":[12],"but":[13],"scaling":[14],"to":[15,61,74,117],"documentlevel":[16],"translation":[18,84],"(DocMT)":[19],"remains":[20],"challenging,":[21],"particularly":[22,144],"modeling":[24],"contexts":[25],"and":[26,31,44,93,105,124,135,148,153],"discourse":[27],"phenomena":[28],"across":[29,131],"sentences":[30],"paragraphs.Document":[32],"translations":[33,64],"generated":[34],"by":[35],"LLMs":[36,60,119],"often":[37],"suffer":[38],"from":[39],"poor":[40],"consistency,":[41],"weak":[42],"coherence,":[43,149],"omission":[45,151],"errors.To":[46],"address":[47],"the":[48,110,114,136,139],"issues,":[49],"we":[50],"propose":[51],"a":[52,76],"novel":[53],"DocMT":[54,133],"framework":[55],"named":[56],"SubDocTrans,":[57],"that":[58],"enables":[59],"produce":[62],"high-quality":[63],"via":[65],"plug-and-play":[66],"multi-granularity":[67,111],"knowledge":[68,95,112],"augmentation.SubDocTrans":[69],"first":[70],"performs":[71],"topic":[72],"segmentation":[73],"divide":[75],"document":[77],"into":[78,113],"coherent":[79],"sub-documents,":[80],"enabling":[81],"efficient":[82],"document-level":[83],"while":[85],"preserving":[86],"contextual":[87],"coherence.For":[88],"each":[89],"sub-document,":[90],"both":[91],"global":[92],"local":[94],"are":[96],"extracted":[97],"including":[98],"bilingual":[99],"summary,":[100],"theme,":[101],"proper":[102],"nouns,":[103],"topics,":[104],"transition":[106],"hint.We":[107],"then":[108],"incorporate":[109],"prompting":[115],"strategy,":[116],"guide":[118],"producing":[121],"consistent,":[122],"coherent,":[123],"accurate":[125],"translations.We":[126],"also":[127],"conduct":[128],"extensive":[129],"experiments":[130],"various":[132],"tasks,":[134],"results":[137],"demonstrate":[138],"effectiveness":[140],"of":[141],"our":[142],"framework,":[143],"improving":[146],"consistency":[147],"reducing":[150],"errors,":[152],"mitigating":[154],"hallucinations.":[155]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}