{"id":"https://openalex.org/W4412888474","doi":"https://doi.org/10.18653/v1/2025.findings-acl.393","title":"DocFusion: A Unified Framework for Document Parsing Tasks","display_name":"DocFusion: A Unified Framework for Document Parsing Tasks","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888474","doi":"https://doi.org/10.18653/v1/2025.findings-acl.393"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.393","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.393","pdf_url":"https://aclanthology.org/2025.findings-acl.393.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.393.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109693861","display_name":"Mingxu Chai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingxu Chai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100308538","display_name":"Ziyu Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyu Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393895","display_name":"Chong Zhang","orcid":"https://orcid.org/0000-0001-9867-4190"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333729","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-5214-2268"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411426","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0001-6117-6745"},"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/A5083173421","display_name":"Shihan Dou","orcid":"https://orcid.org/0009-0002-6013-3035"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shihan Dou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026984917","display_name":"Jihua Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jihua Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043925137","display_name":"Jiazheng Zhang","orcid":"https://orcid.org/0000-0003-1963-791X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiazheng Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014306843","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0002-5203-8778"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Zhang","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7584","last_page":"7599"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9818000197410583,"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":0.9818000197410583,"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/computer-science","display_name":"Computer science","score":0.8429539203643799},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7449126243591309},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5263941287994385},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46867260336875916},{"id":"https://openalex.org/keywords/bottom-up-parsing","display_name":"Bottom-up parsing","score":0.4314889907836914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37910518050193787},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36611419916152954},{"id":"https://openalex.org/keywords/top-down-parsing","display_name":"Top-down parsing","score":0.30204376578330994}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429539203643799},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7449126243591309},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5263941287994385},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46867260336875916},{"id":"https://openalex.org/C60690694","wikidata":"https://www.wikidata.org/wiki/Q894902","display_name":"Bottom-up parsing","level":4,"score":0.4314889907836914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37910518050193787},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36611419916152954},{"id":"https://openalex.org/C42560504","wikidata":"https://www.wikidata.org/wiki/Q15419395","display_name":"Top-down parsing","level":3,"score":0.30204376578330994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.393","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.393","pdf_url":"https://aclanthology.org/2025.findings-acl.393.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.393","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.393","pdf_url":"https://aclanthology.org/2025.findings-acl.393.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":[{"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/W4412888474.pdf","grobid_xml":"https://content.openalex.org/works/W4412888474.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3143982968","https://openalex.org/W3088470625","https://openalex.org/W2952780262","https://openalex.org/W3035970863","https://openalex.org/W2619584063","https://openalex.org/W2970260326","https://openalex.org/W2804916787","https://openalex.org/W2389755172","https://openalex.org/W2142145894","https://openalex.org/W4381248170"],"abstract_inverted_index":{"Document":[0],"parsing":[1,102,130],"involves":[2],"layout":[3],"element":[4],"detection":[5,34,63],"and":[6,26,35,74,140],"recognition,":[7,36],"essential":[8],"for":[9,18],"extracting":[10],"information.However,":[11],"existing":[12],"methods":[13],"often":[14,38],"employ":[15],"multiple":[16],"models":[17,30],"these":[19],"tasks,":[20,131],"leading":[21,68],"to":[22,32,40,69,89,112],"increased":[23],"system":[24],"complexity":[25],"maintenance":[27],"overhead.While":[28],"some":[29],"attempt":[31],"unify":[33],"they":[37],"fail":[39],"address":[41],"the":[42,81,110,133],"intrinsic":[43],"differences":[44],"in":[45,51,71],"data":[46],"representations,":[47],"thereby":[48],"limiting":[49],"performance":[50],"document":[52,101,129],"processing.Our":[53],"research":[54],"reveals":[55],"that":[56,119],"recognition":[57],"relies":[58,64],"on":[59,65],"discrete":[60],"tokens,":[61],"whereas":[62],"continuous":[66],"coordinates,":[67],"challenges":[70],"gradient":[72],"updates":[73],"optimization.To":[75],"bridge":[76],"this":[77],"gap,":[78],"we":[79,96,108],"propose":[80,97],"Gaussian-Kernel":[82],"Cross-Entropy":[83],"Loss":[84],"(GK-CEL),":[85],"enabling":[86],"generative":[87],"frameworks":[88],"handle":[90],"both":[91],"tasks":[92],"simultaneously.Building":[93],"upon":[94],"GK-CEL,":[95,123],"DocFusion,":[98,120],"a":[99],"unified":[100,137],"model":[103,139],"with":[104,122],"only":[105],"0.28B":[106],"parameters.Additionally,":[107],"construct":[109],"DocLatex-1.6Mdataset":[111],"provide":[113],"high-quality":[114],"training":[115],"support.Experimental":[116],"results":[117],"show":[118],"equipped":[121],"performs":[124],"competitively":[125],"across":[126],"four":[127],"core":[128],"validating":[132],"effectiveness":[134],"of":[135],"our":[136],"approach.The":[138],"datasets":[141],"are":[142],"publicly":[143],"available":[144],"at:":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}