{"id":"https://openalex.org/W7155951527","doi":"https://doi.org/10.1145/3774904.3792229","title":"DMAP: Human-Aligned Structural Document Map for Multimodal Document Understanding","display_name":"DMAP: Human-Aligned Structural Document Map for Multimodal Document Understanding","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7155951527","doi":"https://doi.org/10.1145/3774904.3792229"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792229","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792229","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792229","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123910330","display_name":"ShunLiang Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunliang Fu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-0943-5884","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134669225","display_name":"Yanxin Zhang","orcid":"https://orcid.org/0009-0001-2307-901X"},"institutions":[{"id":"https://openalex.org/I4210118284","display_name":"Alliant Energy (United States)","ror":"https://ror.org/02h1ae871","country_code":"US","type":"company","lineage":["https://openalex.org/I4210118284"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanxin Zhang","raw_affiliation_strings":["Independant Study, Madison, USA"],"raw_orcid":"https://orcid.org/0009-0001-2307-901X","affiliations":[{"raw_affiliation_string":"Independant Study, Madison, USA","institution_ids":["https://openalex.org/I4210118284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039420617","display_name":"Y. Xiang","orcid":"https://orcid.org/0000-0002-9423-4865"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Xiang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-6759-7194","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003567218","display_name":"Xiaoyu Du","orcid":"https://orcid.org/0000-0002-4641-1994"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Du","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4641-1994","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035112538","display_name":"Jinhui Tang","orcid":"https://orcid.org/0000-0001-9008-222X"},"institutions":[{"id":"https://openalex.org/I167027274","display_name":"Nanjing Forestry University","ror":"https://ror.org/03m96p165","country_code":"CN","type":"education","lineage":["https://openalex.org/I167027274"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Tang","raw_affiliation_strings":["Nanjing Forestry University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9008-222X","affiliations":[{"raw_affiliation_string":"Nanjing Forestry University, Nanjing, China","institution_ids":["https://openalex.org/I167027274"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":"2037","last_page":"2048"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.652999997138977,"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/T10028","display_name":"Topic Modeling","score":0.652999997138977,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.20589999854564667,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.04280000180006027,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/exploit","display_name":"Exploit","score":0.685699999332428},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5455999970436096},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5318999886512756},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4672999978065491},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4422999918460846},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.43230000138282776},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4316999912261963},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4251999855041504},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.41670000553131104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976999878883362},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.685699999332428},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5455999970436096},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5318999886512756},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4982999861240387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47909998893737793},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4251999855041504},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4088999927043915},{"id":"https://openalex.org/C137441365","wikidata":"https://www.wikidata.org/wiki/Q7981054","display_name":"Well-formed document","level":5,"score":0.37389999628067017},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C2779353889","wikidata":"https://www.wikidata.org/wiki/Q2912668","display_name":"Image schema","level":4,"score":0.28139999508857727},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792229","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792229","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792229","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792229","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W3004268082","https://openalex.org/W3154280800","https://openalex.org/W3217305727","https://openalex.org/W4210451781","https://openalex.org/W4304013646","https://openalex.org/W4382202558","https://openalex.org/W4385237494","https://openalex.org/W4385574225","https://openalex.org/W4389518671","https://openalex.org/W4389523905","https://openalex.org/W4389524238","https://openalex.org/W4389984066","https://openalex.org/W4395686609","https://openalex.org/W4396758677","https://openalex.org/W4396823873","https://openalex.org/W4400524512","https://openalex.org/W4400525588","https://openalex.org/W4400526199","https://openalex.org/W4402671780","https://openalex.org/W4403347014","https://openalex.org/W4404239715","https://openalex.org/W4404330874","https://openalex.org/W4404404855","https://openalex.org/W4404534210","https://openalex.org/W4404782234","https://openalex.org/W4404782892","https://openalex.org/W4404954244","https://openalex.org/W4405792483","https://openalex.org/W4406093428","https://openalex.org/W4409657237","https://openalex.org/W4409657473","https://openalex.org/W4410089370","https://openalex.org/W4410636349","https://openalex.org/W4415311393","https://openalex.org/W4415329582","https://openalex.org/W4416067397","https://openalex.org/W4416260051","https://openalex.org/W6891897994","https://openalex.org/W6891932366"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"multimodal":[1,72,159],"document":[2],"question-answering":[3],"(QA)":[4],"systems":[5],"predominantly":[6],"rely":[7],"on":[8,137],"flat":[9],"semantic":[10,102],"retrieval,":[11],"representing":[12],"documents":[13],"as":[14,37],"a":[15,56,77,95,110],"set":[16],"of":[17,123],"disconnected":[18],"text":[19],"chunks":[20],"and":[21,27,34,42,68,103,116,126,158],"largely":[22],"neglecting":[23],"their":[24],"intrinsic":[25],"hierarchical":[26,66,97],"relational":[28],"structures.":[29],"Such":[30],"flattening":[31],"disrupts":[32],"logical":[33],"spatial":[35],"dependencies\u2014such":[36],"section":[38],"organization,":[39],"figure-text":[40],"correspondence,":[41],"cross-reference":[43],"relations\u2014that":[44],"humans":[45],"naturally":[46],"exploit":[47],"for":[48],"comprehension.":[49],"To":[50],"address":[51],"this":[52,108],"limitation,":[53],"we":[54,75],"introduce":[55],"document-level":[57],"structural":[58,145],"Document":[59],"MAP":[60],"(DMAP),":[61],"which":[62],"explicitly":[63],"encodes":[64],"both":[65,101],"organization":[67],"inter-element":[69],"relationships":[70],"within":[71],"documents.":[73],"Specifically,":[74],"design":[76],"Structured-Semantic":[78],"Understanding":[79],"Agent":[80,113],"to":[81],"construct":[82],"DMAP":[83,142],"by":[84],"organizing":[85],"textual":[86],"content":[87],"together":[88],"with":[89,133,148],"figures,":[90],"tables,":[91],"charts,":[92],"etc":[93],"into":[94],"human-aligned":[96],"schema":[98],"that":[99,141],"captures":[100],"layout":[104],"dependencies.":[105],"Building":[106],"upon":[107],"representation,":[109],"Reflective":[111],"Reasoning":[112],"performs":[114],"structure-aware":[115],"evidence-driven":[117],"reasoning,":[118],"dynamically":[119],"assessing":[120],"the":[121],"sufficiency":[122],"retrieved":[124],"context":[125],"iteratively":[127],"refining":[128],"answers":[129],"through":[130],"targeted":[131],"interactions":[132],"DMAP.":[134],"Extensive":[135],"experiments":[136],"MMDocQA":[138],"benchmarks":[139],"demonstrate":[140],"yields":[143],"document-specific":[144],"representations":[146],"aligned":[147],"human":[149],"interpretive":[150],"patterns,":[151],"substantially":[152],"enhancing":[153],"retrieval":[154],"precision,":[155],"reasoning":[156],"consistency,":[157],"comprehension":[160],"over":[161],"conventional":[162],"RAG-based":[163],"approaches.":[164],"Code":[165],"is":[166],"available":[167],"at":[168],"https://github.com/Forlorin/DMAP":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-28T00:00:00"}