{"id":"https://openalex.org/W7166860167","doi":"https://doi.org/10.18653/v1/2026.acl-demo.25","title":"BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation","display_name":"BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166860167","doi":"https://doi.org/10.18653/v1/2026.acl-demo.25"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-demo.25","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-demo.25","pdf_url":"https://aclanthology.org/2026.acl-demo.25.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-demo.25.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139848198","display_name":"Yang Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057387191","display_name":"Xiangyao Ma","orcid":"https://orcid.org/0000-0001-6694-4037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyao Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139764218","display_name":"Xiao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139793910","display_name":"Hao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139771966","display_name":"Rui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Wang","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84868071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7451000213623047,"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":0.7451000213623047,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.04190000146627426,"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/T11269","display_name":"Algorithms and Data Compression","score":0.03660000115633011,"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/representation","display_name":"Representation (politics)","score":0.4975999891757965},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.46560001373291016},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2806999981403351},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.2599000036716461},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.25699999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5579000115394592},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4975999891757965},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.46560001373291016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45669999718666077},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35600000619888306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31709998846054077},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-demo.25","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-demo.25","pdf_url":"https://aclanthology.org/2026.acl-demo.25.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-demo.25","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-demo.25","pdf_url":"https://aclanthology.org/2026.acl-demo.25.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3879535228","display_name":null,"funder_award_id":"62306173","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/W7166860167.pdf","grobid_xml":"https://content.openalex.org/works/W7166860167.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"global":[1],"cross-lingual":[2],"communication":[3],"intensifies,":[4],"language":[5],"barriers":[6],"in":[7],"visually":[8],"rich":[9],"documents":[10],"such":[11,75],"as":[12,76],"PDFs":[13],"remain":[14],"a":[15,22,102],"practical":[16],"bottleneck.Existing":[17],"document":[18,40],"translation":[19,73,131],"pipelines":[20],"face":[21],"tension":[23],"between":[24],"linguistic":[25],"processing":[26],"and":[27,45,84,110,122,135,143,150],"layout":[28,66,95,118],"preservation:":[29],"text-oriented":[30],"Computer-Assisted":[31],"Translation":[32],"(CAT)":[33],"systems":[34],"often":[35],"discard":[36],"structural":[37],"metadata,":[38],"while":[39,128],"parsers":[41],"focus":[42],"on":[43,101],"extraction":[44],"do":[46],"not":[47],"support":[48],"faithful":[49],"re-rendering":[50],"after":[51],"translation.We":[52],"introduce":[53],"BabelDOC,":[54],"an":[55,97],"Intermediate":[56],"Representation":[57],"(IR)-based":[58],"framework":[59],"for":[60],"layout-preserving":[61],"PDF":[62],"translation.BabelDOC":[63],"decouples":[64],"visual":[65,120],"metadata":[67],"from":[68],"semantic":[69],"content,":[70],"enabling":[71],"documentlevel":[72],"operations":[74],"terminology":[77,123],"extraction,":[78],"cross-page":[79],"context":[80],"handling,":[81],"glossary-constrained":[82],"generation,":[83],"formula":[85],"placeholdering.The":[86],"translated":[87],"content":[88],"is":[89],"then":[90],"re-anchored":[91],"to":[92],"the":[93,154],"original":[94],"through":[96],"adaptive":[98],"typesetting":[99],"engine.Experiments":[100],"curated":[103],"200-page":[104],"benchmark,":[105],"together":[106],"with":[107],"human":[108],"evaluation":[109],"multimodal":[111],"LLM-as-ajudge":[112],"evaluation,":[113],"show":[114],"that":[115],"BabelDOC":[116],"improves":[117],"fidelity,":[119],"aesthetics,":[121],"consistency":[124],"over":[125,146],"representative":[126],"baselines,":[127],"maintaining":[129],"competitive":[130],"precision.The":[132],"open-source":[133],"toolkit":[134],"its":[136],"interactive":[137],"downstream":[138],"applications":[139],"are":[140],"publicly":[141],"available":[142],"have":[144],"attracted":[145],"8.4K":[147],"GitHub":[148],"stars":[149],"17":[151],"contributors":[152],"at":[153],"time":[155],"of":[156],"writing:":[157],"https:":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}