{"id":"https://openalex.org/W4389518982","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.604","title":"On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval","display_name":"On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389518982","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.604"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.604","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.604","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.findings-emnlp.604","pdf_url":"https://aclanthology.org/2023.findings-emnlp.604.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.findings-emnlp.604.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100609080","display_name":"Jiayi Chen","orcid":"https://orcid.org/0000-0002-3541-8410","observed_orcids":["https://orcid.org/0000-0002-3541-8410","https://orcid.org/0009-0000-1297-4572","https://orcid.org/0009-0006-2822-7137","https://orcid.org/0000-0001-9861-3582"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayi Chen","raw_affiliation_strings":["University of Virginia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040269658","display_name":"Hanjun Dai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanjun Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062711588","display_name":"Bo Dai","orcid":"https://orcid.org/0000-0002-0029-792X","observed_orcids":["https://orcid.org/0000-0002-0029-792X"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Dai","raw_affiliation_strings":["Georgia Institute of Technology , 3 Accenture 4 Google , Mountain View , USA","Georgia Institute of Technology,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , 3 Accenture 4 Google , Mountain View , USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology,","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013588572","display_name":"Aidong Zhang","orcid":"https://orcid.org/0000-0001-9723-3246","observed_orcids":["https://orcid.org/0000-0001-9723-3246"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aidong Zhang","raw_affiliation_strings":["University of Virginia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100323752","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-7566-2995","observed_orcids":["https://orcid.org/0000-0002-7566-2995"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Accenture 4 Google, Mountain View, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Accenture 4 Google, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2037,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5669429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9006","last_page":"9025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8637999892234802,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8637999892234802,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10599999874830246,"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":0.018400000408291817,"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/meta-learning","display_name":"meta-learning","score":0.8960000276565552},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"multimodal learning","score":0.7379999756813049},{"id":"https://openalex.org/keywords/document-images","display_name":"scanned documents","score":0.5180000066757202},{"id":"https://openalex.org/keywords/out-of-distribution-robustness","display_name":"out-of-distribution robustness","score":0.7269999980926514},{"id":"https://openalex.org/keywords/hierarchical-decoder","display_name":"hierarchical decoder","score":0.8450000286102295},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.9549999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8658807277679443},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5817950963973999},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5332016348838806},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5239836573600769},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5195277333259583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47201985120773315},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3356529772281647},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17007315158843994},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.11042091250419617},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.findings-emnlp.604","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.604","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.findings-emnlp.604","pdf_url":"https://aclanthology.org/2023.findings-emnlp.604.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2311.00693","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.00693","pdf_url":"https://arxiv.org/pdf/2311.00693","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.00693","doi":"https://doi.org/10.48550/arxiv.2311.00693","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.00693","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.604","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.604","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.findings-emnlp.604","pdf_url":"https://aclanthology.org/2023.findings-emnlp.604.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389518982.pdf","grobid_xml":"https://content.openalex.org/works/W4389518982.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W2130723172","https://openalex.org/W2166706236","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2565019508","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2795900505","https://openalex.org/W2803672301","https://openalex.org/W2805481182","https://openalex.org/W2884901161","https://openalex.org/W2896457183","https://openalex.org/W2922714365","https://openalex.org/W2947697927","https://openalex.org/W2963341924","https://openalex.org/W2974885182","https://openalex.org/W2996769125","https://openalex.org/W3000758063","https://openalex.org/W3003484198","https://openalex.org/W3009328596","https://openalex.org/W3012080662","https://openalex.org/W3018378048","https://openalex.org/W3030163527","https://openalex.org/W3088403594","https://openalex.org/W3091905774","https://openalex.org/W3093218477","https://openalex.org/W3102719996","https://openalex.org/W3103390191","https://openalex.org/W3104774463","https://openalex.org/W3104953317","https://openalex.org/W3108847140","https://openalex.org/W3129576130","https://openalex.org/W3132244696","https://openalex.org/W3137110532","https://openalex.org/W3158362813","https://openalex.org/W3165374601","https://openalex.org/W3169708801","https://openalex.org/W3171163219","https://openalex.org/W3176664887","https://openalex.org/W3176851559","https://openalex.org/W3194594797","https://openalex.org/W3199589346","https://openalex.org/W3200439183","https://openalex.org/W3202466114","https://openalex.org/W3208059549","https://openalex.org/W3211361348","https://openalex.org/W3212769596","https://openalex.org/W3214042621","https://openalex.org/W4213450898","https://openalex.org/W4221149336","https://openalex.org/W4224095956","https://openalex.org/W4224107812","https://openalex.org/W4224309761","https://openalex.org/W4226020328","https://openalex.org/W4287123554","https://openalex.org/W4287827961","https://openalex.org/W4290945297","https://openalex.org/W4304013646","https://openalex.org/W4319163914","https://openalex.org/W4366083832","https://openalex.org/W4384891056","https://openalex.org/W4385570166","https://openalex.org/W4385571117","https://openalex.org/W4385990987","https://openalex.org/W4386076681","https://openalex.org/W4389519230"],"related_works":["https://openalex.org/W4402684134","https://openalex.org/W4389519230","https://openalex.org/W4402335442","https://openalex.org/W4403780729","https://openalex.org/W4224107812","https://openalex.org/W4367554059","https://openalex.org/W4389519297","https://openalex.org/W7203472932","https://openalex.org/W3104774463","https://openalex.org/W4389519195"],"abstract_inverted_index":{"Visually-rich":[0],"document":[1,12,30,85],"entity":[2,40,50,91,102,111],"retrieval":[3],"(VDER),":[4],"which":[5,93],"extracts":[6],"key":[7],"information":[8],"(e.g.date,":[9],"address)":[10],"from":[11],"images":[13],"like":[14],"invoices":[15],"and":[16,110,142,174,183],"receipts,":[17],"has":[18],"become":[19],"an":[20],"important":[21],"topic":[22],"in":[23,70,132,202],"industrial":[24],"NLP":[25],"applications.The":[26],"emergence":[27],"of":[28,57,67,135,146,205,217],"new":[29,195],"types":[31,51,103],"at":[32,83],"a":[33,43,55,71,88,124,156,162,179,194],"constant":[34],"pace,":[35],"each":[36,108,140],"with":[37,87,161],"its":[38],"unique":[39,44],"types,":[41],"presents":[42],"challenge:":[45],"many":[46],"documents":[47],"contain":[48],"unseen":[49],"that":[52,170],"occur":[53],"only":[54],"couple":[56],"times.Addressing":[58],"this":[59,118,121,151,190],"challenge":[60],"requires":[61],"models":[62],"to":[63,188,198],"have":[64],"the":[65,81,84,97,133,136,143,203,215],"ability":[66],"learning":[68,186],"entities":[69],"few-shot":[72,99,127,207],"manner.However,":[73],"prior":[74],"works":[75],"for":[76,96,139],"Few-shot":[77],"VDER":[78,128],"mainly":[79],"address":[80,117],"problem":[82],"level":[86],"predefined":[89],"global":[90],"space,":[92],"doesn't":[94],"account":[95],"entity-level":[98,126,206],"scenario:":[100],"target":[101],"are":[104],"locally":[105],"personalized":[106],"by":[107],"task":[109,141,168],"occurrences":[112],"vary":[113],"significantly":[114,213],"among":[115],"documents.To":[116],"unexplored":[119],"scenario,":[120],"paper":[122],"studies":[123],"novel":[125,152],"task.The":[129],"challenges":[130],"lie":[131],"uniqueness":[134],"label":[137],"space":[138],"increased":[144],"complexity":[145],"out-of-distribution":[147],"(OOD)":[148],"contents.To":[149],"tackle":[150],"task,":[153],"we":[154,177,192],"present":[155],"task-aware":[157],"meta-learning":[158,219],"based":[159],"framework,":[160],"central":[163],"focus":[164],"on":[165],"achieving":[166],"effective":[167],"personalization":[169],"distinguishes":[171],"between":[172],"intask":[173],"out-of-task":[175],"distribution.Specifically,":[176],"adopt":[178],"hierarchical":[180],"decoder":[181],"(HC)":[182],"employ":[184],"contrastive":[185],"(ContrastProtoNet)":[187],"achieve":[189],"goal.Furthermore,":[191],"introduce":[193],"dataset,":[196],"FewVEX,":[197],"boost":[199],"future":[200],"research":[201],"field":[204],"VDER.Experimental":[208],"results":[209],"demonstrate":[210],"our":[211],"approaches":[212],"improve":[214],"robustness":[216],"popular":[218],"baselines.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-12-10T00:00:00"}