{"id":"https://openalex.org/W4412944696","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1213","title":"Improving MLLM\u2019s Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency","display_name":"Improving MLLM\u2019s Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944696","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1213"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1213","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1213","pdf_url":"https://aclanthology.org/2025.findings-acl.1213.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.1213.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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/A5100366785","display_name":"Yaping Zhang","orcid":"https://orcid.org/0009-0002-7674-2409"},"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/A5100633382","display_name":"Zhiyang Zhang","orcid":"https://orcid.org/0000-0002-6766-8449"},"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/A5100438505","display_name":"Zhiyuan Chen","orcid":"https://orcid.org/0000-0001-6357-2135"},"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/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/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/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":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016175345","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0003-4188-9953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhou","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23659","last_page":"23678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9793999791145325,"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":0.9793999791145325,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9659000039100647,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9215999841690063,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7708874940872192},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6835814118385315},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6015732288360596},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5839463472366333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5711663961410522},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5549243688583374},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.47033554315567017},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4503893554210663},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41157642006874084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4102585017681122},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.21960249543190002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7708874940872192},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6835814118385315},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6015732288360596},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5839463472366333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5711663961410522},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5549243688583374},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.47033554315567017},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4503893554210663},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41157642006874084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4102585017681122},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.21960249543190002},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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.1213","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1213","pdf_url":"https://aclanthology.org/2025.findings-acl.1213.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.1213","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1213","pdf_url":"https://aclanthology.org/2025.findings-acl.1213.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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944696.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2131730163","https://openalex.org/W2038329042","https://openalex.org/W2573990671","https://openalex.org/W2043611036","https://openalex.org/W4388916331","https://openalex.org/W2543788071","https://openalex.org/W2039452999","https://openalex.org/W3021512437"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
