{"id":"https://openalex.org/W4416033990","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1088","title":"Intelligent Document Parsing: Towards End-to-end Document Parsing via Decoupled Content Parsing and Layout Grounding","display_name":"Intelligent Document Parsing: Towards End-to-end Document Parsing via Decoupled Content Parsing and Layout Grounding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033990","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1088"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1088","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1088","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1088.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1088.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039720488","display_name":"Hangdi Xing","orcid":"https://orcid.org/0000-0002-1770-005X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hangdi Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038757890","display_name":"Feiyu Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feiyu Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750527","display_name":"Qi Zheng","orcid":"https://orcid.org/0009-0001-3822-2616"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007608248","display_name":"Zhaoqing Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoqing Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005050646","display_name":"Zirui Shao","orcid":"https://orcid.org/0000-0002-4210-070X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zirui Shao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000844861","display_name":"Ming Yan","orcid":"https://orcid.org/0000-0002-4388-6708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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":0.1567772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19987","last_page":"19998"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5221999883651733,"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":0.5221999883651733,"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":0.24310000240802765,"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":0.020600000396370888,"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/parsing","display_name":"Parsing","score":0.6692000031471252},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4593999981880188},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41019999980926514},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.32850000262260437},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.27000001072883606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379999756813049},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6692000031471252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5180000066757202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5044999718666077},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4081999957561493},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1088","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1088","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1088.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.1088","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1088","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1088.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":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033990.pdf","grobid_xml":"https://content.openalex.org/works/W4416033990.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,31,35,41,62,84,96,113,122,132],"daily":[2],"work,":[3],"vast":[4],"amounts":[5],"of":[6,37,99,124],"documents":[7],"are":[8],"stored":[9],"in":[10,46],"pixel-based":[11],"formats":[12],"such":[13],"as":[14],"images":[15],"and":[16,25,49,108,116],"scanned":[17],"PDFs,":[18],"posing":[19],"challenges":[20],"for":[21,76,126],"efficient":[22],"database":[23],"management":[24],"data":[26],"processing.Existing":[27],"methods":[28],"often":[29],"fragment":[30],"parsing":[32,93,115],"process":[33],"into":[34],"pipeline":[36],"separated":[38],"subtasks":[39],"on":[40,55],"layout":[42,117],"element":[43],"level,":[44],"resulting":[45],"incomplete":[47],"semantics":[48],"error":[50],"propagation.Even":[51],"though":[52],"models":[53,59],"based":[54],"multimodal":[56],"large":[57],"language":[58],"(MLLMs)":[60],"mitigate":[61],"issues":[63],"to":[64,111,119],"some":[65],"extent,":[66],"they":[67],"also":[68],"suffer":[69],"from":[70],"absent":[71],"or":[72],"sub-optimal":[73],"grounding":[74,118],"ability":[75],"visual":[77],"information.To":[78],"address":[79],"these":[80],"challenges,":[81],"we":[82],"introduce":[83],"Intelligent":[85],"Document":[86],"Parsing":[87],"(IDP)":[88],"framework,":[89],"an":[90,103],"end-to-end":[91],"document":[92,106,127,141],"framework":[94],"leveraging":[95],"visionlanguage":[97],"priors":[98],"MLLMs,":[100],"equipped":[101],"with":[102],"elaborately":[104],"designed":[105],"representation":[107],"decoding":[109],"mechanism":[110],"decouple":[112],"content":[114],"fully":[120],"activate":[121],"potential":[123],"MLLMs":[125],"parsing.Experimental":[128],"results":[129],"demonstrate":[130],"that":[131],"IDP":[133],"method":[134],"surpasses":[135],"existing":[136],"methods,":[137],"significantly":[138],"advancing":[139],"MLLM-based":[140],"parsing.":[142]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}