{"id":"https://openalex.org/W4297678984","doi":"https://doi.org/10.1145/3503161.3548422","title":"Towards Complex Document Understanding By Discrete Reasoning","display_name":"Towards Complex Document Understanding By Discrete Reasoning","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4297678984","doi":"https://doi.org/10.1145/3503161.3548422"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548422","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029052244","display_name":"Fengbin Zhu","orcid":"https://orcid.org/0000-0001-6776-2040"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Fengbin Zhu","raw_affiliation_strings":["National University of Singapore & 6Estates Pte Ltd, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore & 6Estates Pte Ltd, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039239180","display_name":"Wenqiang Lei","orcid":"https://orcid.org/0000-0001-6540-0601"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqiang Lei","raw_affiliation_strings":["Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051925942","display_name":"Fuli Feng","orcid":"https://orcid.org/0000-0002-5828-9842"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuli Feng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115076700","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-4887-923X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["6Estates Pte Ltd, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"6Estates Pte Ltd, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003475089","display_name":"Haozhou Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhou Zhang","raw_affiliation_strings":["Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087041599","display_name":"Tat-Seng Chua","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5029052244"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.3821,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.87444105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4857","last_page":"4866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.8269433975219727},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.762798547744751},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6168578267097473},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5685699582099915},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5344055891036987},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5080902576446533},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.45548903942108154},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4428150951862335},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4191203713417053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4181830883026123},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2167404592037201}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8269433975219727},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.762798547744751},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6168578267097473},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5685699582099915},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5344055891036987},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5080902576446533},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.45548903942108154},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4428150951862335},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4191203713417053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4181830883026123},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2167404592037201},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548422","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1847618513","https://openalex.org/W2251349042","https://openalex.org/W2757276219","https://openalex.org/W2758343314","https://openalex.org/W2963705839","https://openalex.org/W2963748441","https://openalex.org/W2963899988","https://openalex.org/W2964710271","https://openalex.org/W2970609357","https://openalex.org/W2970900584","https://openalex.org/W2988326850","https://openalex.org/W2990138404","https://openalex.org/W2997154779","https://openalex.org/W3003711898","https://openalex.org/W3035140194","https://openalex.org/W3035498813","https://openalex.org/W3098324846","https://openalex.org/W3100618740","https://openalex.org/W3104953317","https://openalex.org/W3107064625","https://openalex.org/W3113753692","https://openalex.org/W3121976951","https://openalex.org/W3165753548","https://openalex.org/W3168052339","https://openalex.org/W3173585224","https://openalex.org/W4205508242","https://openalex.org/W4238846128","https://openalex.org/W4239019441","https://openalex.org/W4285199586"],"related_works":["https://openalex.org/W3204607391","https://openalex.org/W2964413124","https://openalex.org/W3157284875","https://openalex.org/W1984061923","https://openalex.org/W2259406085","https://openalex.org/W3113264705","https://openalex.org/W2099715052","https://openalex.org/W4213176082","https://openalex.org/W4220955952","https://openalex.org/W1566366091"],"abstract_inverted_index":{"Document":[0,19,158],"Visual":[1],"Question":[2],"Answering":[3],"(VQA)":[4],"aims":[5],"to":[6,61,84,154],"answer":[7,62],"questions":[8,90],"over":[9],"visually-rich":[10,136],"documents.":[11],"In":[12],"this":[13],"work,":[14],"we":[15,68,146],"introduce":[16],"a":[17,71],"new":[18],"VQA":[20,159],"dataset,":[21],"named":[22,74],"TAT-DQA,":[23,67],"which":[24,54],"consists":[25],"of":[26,52,89,120,135],"3,067":[27],"document":[28],"pages":[29],"comprising":[30],"semi-structured":[31],"table(s)":[32],"and":[33,49],"unstructured":[34],"text":[35],"as":[36,38],"well":[37],"16,558":[39],"question-answer":[40],"pairs.":[41],"The":[42,98],"documents":[43],"are":[44],"sampled":[45],"from":[46],"financial":[47],"reports":[48],"contain":[50],"lots":[51],"numbers,":[53],"means":[55],"discrete":[56,143],"reasoning":[57],"capability":[58],"is":[59],"demanded":[60],"the":[63,80,106,113,131,148],"questions.":[64],"Based":[65],"on":[66,133],"further":[69],"develop":[70],"novel":[72],"model":[73,103,150],"MHST":[75,102],"that":[76,101,119,125,141],"takes":[77],"into":[78],"account":[79],"information":[81],"in":[82,161],"multi-modalities":[83],"intelligently":[85],"address":[86],"different":[87],"types":[88],"with":[91],"corresponding":[92],"strategies,":[93],"i.e.,":[94],"extraction":[95],"or":[96],"reasoning.":[97,144],"experiments":[99],"show":[100],"significantly":[104],"outperforms":[105],"baseline":[107],"methods,":[108],"demonstrating":[109],"its":[110],"effectiveness.":[111],"However,":[112],"performance":[114],"still":[115],"lags":[116],"far":[117],"behind":[118],"expert":[121],"humans.":[122],"We":[123],"expect":[124],"our":[126],"TAT-DQA":[127],"dataset":[128],"would":[129,151],"facilitate":[130],"research":[132],"understanding":[134],"documents,":[137],"especially":[138],"for":[139],"scenarios":[140],"require":[142],"Also,":[145],"hope":[147],"proposed":[149],"inspire":[152],"researchers":[153],"design":[155],"more":[156],"advanced":[157],"models":[160],"future.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}