{"id":"https://openalex.org/W7169667884","doi":"https://doi.org/10.1007/978-981-92-3520-9_46","title":"MGL-LMM: Generative OCR with Semantic Inpainting for Degraded Mongolian Lead-Type Printed Documents","display_name":"MGL-LMM: Generative OCR with Semantic Inpainting for Degraded Mongolian Lead-Type Printed Documents","publication_year":2026,"publication_date":"2026-07-18","ids":{"openalex":"https://openalex.org/W7169667884","doi":"https://doi.org/10.1007/978-981-92-3520-9_46"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-92-3520-9_46","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-92-3520-9_46","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-981-92-3520-9_46.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-981-92-3520-9_46.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140524453","display_name":"Zicheng Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I55654194","display_name":"Inner Mongolia University of Technology","ror":"https://ror.org/05564e019","country_code":"CN","type":"education","lineage":["https://openalex.org/I55654194"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zicheng Luo","raw_affiliation_strings":["College of Intelligent Science and Technology (College of Cyberspace Security), Inner Mongolia University of Technology, Hohhot, 010080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligent Science and Technology (College of Cyberspace Security), Inner Mongolia University of Technology, Hohhot, 010080, China","institution_ids":["https://openalex.org/I55654194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141132531","display_name":"Min Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I55654194","display_name":"Inner Mongolia University of Technology","ror":"https://ror.org/05564e019","country_code":"CN","type":"education","lineage":["https://openalex.org/I55654194"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Lu","raw_affiliation_strings":["College of Intelligent Science and Technology (College of Cyberspace Security), Inner Mongolia University of Technology, Hohhot, 010080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligent Science and Technology (College of Cyberspace Security), Inner Mongolia University of Technology, Hohhot, 010080, China","institution_ids":["https://openalex.org/I55654194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141116739","display_name":"Na Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I55654194","display_name":"Inner Mongolia University of Technology","ror":"https://ror.org/05564e019","country_code":"CN","type":"education","lineage":["https://openalex.org/I55654194"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Na Liu","raw_affiliation_strings":["College of Intelligent Science and Technology (College of Cyberspace Security), Inner Mongolia University of Technology, Hohhot, 010080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligent Science and Technology (College of Cyberspace Security), Inner Mongolia University of Technology, Hohhot, 010080, China","institution_ids":["https://openalex.org/I55654194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124130118","display_name":"Bao Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I55654194","display_name":"Inner Mongolia University of Technology","ror":"https://ror.org/05564e019","country_code":"CN","type":"education","lineage":["https://openalex.org/I55654194"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bao Shi","raw_affiliation_strings":["College of Intelligent Science and Technology (College of Cyberspace Security), Inner Mongolia University of Technology, Hohhot, 010080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligent Science and Technology (College of Cyberspace Security), Inner Mongolia University of Technology, Hohhot, 010080, China","institution_ids":["https://openalex.org/I55654194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036141569","display_name":"\u4ec1\u5e86\u9053\u5c14\u5409","orcid":null},"institutions":[{"id":"https://openalex.org/I55654194","display_name":"Inner Mongolia University of Technology","ror":"https://ror.org/05564e019","country_code":"CN","type":"education","lineage":["https://openalex.org/I55654194"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingdaoerji Ren","raw_affiliation_strings":["College of Intelligent Science and Technology (College of Cyberspace Security), Inner Mongolia University of Technology, Hohhot, 010080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligent Science and Technology (College of Cyberspace Security), Inner Mongolia University of Technology, Hohhot, 010080, China","institution_ids":["https://openalex.org/I55654194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5141125174","display_name":"Nier Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I55654194","display_name":"Inner Mongolia University of Technology","ror":"https://ror.org/05564e019","country_code":"CN","type":"education","lineage":["https://openalex.org/I55654194"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nier Wu","raw_affiliation_strings":["College of Intelligent Science and Technology (College of Cyberspace Security), Inner Mongolia University of Technology, Hohhot, 010080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligent Science and Technology (College of Cyberspace Security), Inner Mongolia University of Technology, Hohhot, 010080, China","institution_ids":["https://openalex.org/I55654194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5141116739","https://openalex.org/A5141132531"],"corresponding_institution_ids":["https://openalex.org/I55654194"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"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":"581","last_page":"591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7662000060081482},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5475000143051147},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.5194000005722046},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4832000136375427},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4537000060081482},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.4489000141620636},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.42969998717308044},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4203000068664551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8899999856948853},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7662000060081482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7063000202178955},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5475000143051147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5364000201225281},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.5194000005722046},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4832000136375427},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4537000060081482},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.42969998717308044},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C142816647","wikidata":"https://www.wikidata.org/wiki/Q5573018","display_name":"Glyph (data visualization)","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-92-3520-9_46","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-92-3520-9_46","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-981-92-3520-9_46.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-981-92-3520-9_46","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-92-3520-9_46","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-981-92-3520-9_46.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2739592066","display_name":null,"funder_award_id":"2025QN06005","funder_id":"https://openalex.org/F4320322868","funder_display_name":"Natural Science Foundation of Inner Mongolia"},{"id":"https://openalex.org/G549843813","display_name":null,"funder_award_id":"2025MS06039","funder_id":"https://openalex.org/F4320322868","funder_display_name":"Natural Science Foundation of Inner Mongolia"},{"id":"https://openalex.org/G6556899218","display_name":null,"funder_award_id":"2024MS06009","funder_id":"https://openalex.org/F4320322868","funder_display_name":"Natural Science Foundation of Inner Mongolia"},{"id":"https://openalex.org/G7614762891","display_name":null,"funder_award_id":"DC2300001262","funder_id":"https://openalex.org/F4320325744","funder_display_name":"Inner Mongolia University of Technology"}],"funders":[{"id":"https://openalex.org/F4320322216","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496"},{"id":"https://openalex.org/F4320322868","display_name":"Natural Science Foundation of Inner Mongolia","ror":null},{"id":"https://openalex.org/F4320325744","display_name":"Inner Mongolia University of Technology","ror":"https://ror.org/05564e019"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7169667884.pdf","grobid_xml":"https://content.openalex.org/works/W7169667884.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2194187530","https://openalex.org/W2296073425","https://openalex.org/W2809273748","https://openalex.org/W3082397598","https://openalex.org/W3168156488","https://openalex.org/W3181186176","https://openalex.org/W4214753187","https://openalex.org/W4312233877","https://openalex.org/W4312879041","https://openalex.org/W4317497203","https://openalex.org/W4402716156","https://openalex.org/W4402951581","https://openalex.org/W7133193597","https://openalex.org/W7133196460"],"related_works":[],"abstract_inverted_index":{"Digitizing":[0],"historical":[1],"Mongolian":[2],"newspapers":[3],"is":[4,152],"challenging":[5],"due":[6],"to":[7,78,106,111,140],"severe":[8,161],"degradation":[9],"and":[10,16,116],"unique":[11],"script":[12],"properties.":[13],"Elongated":[14],"words":[15],"artifacts,":[17],"like":[18],"ink":[19],"bleeding":[20],"cause":[21],"geometric":[22],"distortion.":[23,61],"These":[24],"issues":[25],"limit":[26],"traditional":[27],"OCR":[28,39],"performance.":[29],"To":[30,62],"address":[31],"these":[32],"issues,":[33],"we":[34,65],"propose":[35],"MGL-LMM,":[36],"a":[37,50,67,92],"Generative":[38],"Paradigm":[40],"specifically":[41],"designed":[42],"for":[43,120],"degraded":[44],"agglutinative":[45],"scripts.":[46],"Our":[47],"framework":[48],"integrates":[49],"topology-preserving":[51],"visual":[52,84,114,158],"normalization":[53],"strategy.":[54],"This":[55,102,142],"maintains":[56],"structural":[57],"integrity":[58],"under":[59,160],"anisotropic":[60],"stabilize":[63],"training,":[64],"employ":[66],"decoupled":[68],"curriculum":[69],"learning":[70],"scheme":[71],"that":[72,126,146],"transitions":[73],"from":[74,138],"word-level":[75],"glyph":[76],"morphologies":[77],"line-level":[79],"contextualization.":[80],"By":[81],"projecting":[82],"high-fidelity":[83],"features":[85],"directly":[86],"into":[87],"the":[88,104,133],"semantic":[89,118],"space":[90],"of":[91],"1.5B-scale":[93],"Large":[94],"Language":[95],"Model,":[96],"MGL-LMM":[97],"performs":[98],"end-to-end":[99],"generative":[100,147],"reasoning.":[101],"allows":[103],"model":[105],"leverage":[107],"contextual":[108],"language":[109,150],"priors":[110,151],"effectively":[112],"reduce":[113],"ambiguities":[115],"provide":[117],"restoration":[119],"obscured":[121],"characters.":[122],"Extensive":[123],"experiments":[124],"demonstrate":[125],"our":[127],"method":[128],"achieves":[129],"state-of-the-art":[130],"performance,":[131],"reducing":[132],"Character":[134],"Error":[135],"Rate":[136],"(CER)":[137],"27%":[139],"11%.":[141],"significant":[143],"improvement":[144],"demonstrates":[145],"decoding":[148],"with":[149],"fundamentally":[153],"more":[154],"effective":[155],"than":[156],"purely":[157],"recognition":[159],"degradation.":[162]},"counts_by_year":[],"updated_date":"2026-07-20T05:51:44.042241","created_date":"2026-07-19T00:00:00"}