{"id":"https://openalex.org/W4402457572","doi":"https://doi.org/10.1145/3650212.3680314","title":"VRDSynth: Synthesizing Programs for Multilingual Visually Rich Document Information Extraction","display_name":"VRDSynth: Synthesizing Programs for Multilingual Visually Rich Document Information Extraction","publication_year":2024,"publication_date":"2024-09-11","ids":{"openalex":"https://openalex.org/W4402457572","doi":"https://doi.org/10.1145/3650212.3680314"},"language":"en","primary_location":{"id":"doi:10.1145/3650212.3680314","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650212.3680314","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 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3650212.3680314","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091080056","display_name":"Thanh-Dat Nguyen","orcid":"https://orcid.org/0000-0002-7751-6510"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Thanh-Dat Nguyen","raw_affiliation_strings":["University of Melbourne, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7751-6510","affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103305897","display_name":"Tung Do-Viet","orcid":"https://orcid.org/0000-0002-2055-5121"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tung Do-Viet","raw_affiliation_strings":["Cinnamon AI, Ho Chi Minh, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-2055-5121","affiliations":[{"raw_affiliation_string":"Cinnamon AI, Ho Chi Minh, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107154347","display_name":"Hung Nguyen-Duy","orcid":"https://orcid.org/0000-0001-5039-4923"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung Nguyen-Duy","raw_affiliation_strings":["Independent Researcher, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0000-0001-5039-4923","affiliations":[{"raw_affiliation_string":"Independent Researcher, Hanoi, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107059273","display_name":"Tuan-Hai Luu","orcid":"https://orcid.org/0009-0008-7524-951X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuan-Hai Luu","raw_affiliation_strings":["Cinnamon AI, Ho Chi Minh, Vietnam"],"raw_orcid":"https://orcid.org/0009-0008-7524-951X","affiliations":[{"raw_affiliation_string":"Cinnamon AI, Ho Chi Minh, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101936199","display_name":"Hung L\u00ea","orcid":"https://orcid.org/0000-0002-3126-184X"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hung Le","raw_affiliation_strings":["Deakin University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3126-184X","affiliations":[{"raw_affiliation_string":"Deakin University, Melbourne, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075260906","display_name":"Xuan-Bach D. Le","orcid":"https://orcid.org/0000-0001-5044-1582"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bach Le","raw_affiliation_strings":["University of Melbourne, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5044-1582","affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040320723","display_name":"Patanamon Thongtanunam","orcid":"https://orcid.org/0000-0001-6328-8839"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Patanamon Thongtanunam","raw_affiliation_strings":["University of Melbourne, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6328-8839","affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5091080056"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":0.3311,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65646463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"704","last_page":"716"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8115594983100891},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5979905724525452},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5961456894874573},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4906834363937378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4616687595844269},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4559105634689331},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33002424240112305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115594983100891},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5979905724525452},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5961456894874573},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4906834363937378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4616687595844269},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4559105634689331},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33002424240112305},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3650212.3680314","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650212.3680314","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 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3650212.3680314","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650212.3680314","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 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1975869473","https://openalex.org/W2055906546","https://openalex.org/W2069065514","https://openalex.org/W2087291337","https://openalex.org/W2106571683","https://openalex.org/W2132525863","https://openalex.org/W2136288796","https://openalex.org/W2148065723","https://openalex.org/W2156279557","https://openalex.org/W2170726034","https://openalex.org/W2560662850","https://openalex.org/W2772286437","https://openalex.org/W2788734534","https://openalex.org/W2889224519","https://openalex.org/W2910204069","https://openalex.org/W2944931850","https://openalex.org/W2947774097","https://openalex.org/W2951087161","https://openalex.org/W2963687456","https://openalex.org/W2988809464","https://openalex.org/W3003206728","https://openalex.org/W3160173210","https://openalex.org/W3172096524","https://openalex.org/W4233597367","https://openalex.org/W4234222550","https://openalex.org/W4281718290","https://openalex.org/W4304013646","https://openalex.org/W4312932486","https://openalex.org/W4315605888","https://openalex.org/W4362707051","https://openalex.org/W4389524198","https://openalex.org/W4402670523","https://openalex.org/W6892864002"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2377297411","https://openalex.org/W3148217948","https://openalex.org/W2375788636","https://openalex.org/W2358561207","https://openalex.org/W2388704129","https://openalex.org/W2392827053","https://openalex.org/W2975617233","https://openalex.org/W2377877252","https://openalex.org/W2368651715"],"abstract_inverted_index":{"Businesses":[0],"often":[1],"need":[2],"to":[3,24,35,107,111,124,144,170,176,191,268],"query":[4],"visually":[5],"rich":[6],"documents":[7],"(VRDs),":[8],"e.g.,":[9,78,93],"purchase":[10,50],"receipts,":[11,51],"medical":[12],"records,":[13],"and":[14,88,149,155,181,187,209,284,289,295],"insurance":[15],"forms,":[16],"among":[17],"many":[18],"other":[19],"forms":[20,220],"from":[21,42,49,115],"multiple":[22],"vendors,":[23],"make":[25],"informed":[26],"decisions.":[27],"As":[28],"such,":[29],"several":[30],"techniques":[31,69],"have":[32,71],"been":[33],"proposed":[34],"automatically":[36,108],"extract":[37,112],"independent":[38],"entities":[39,169],"of":[40,85,164,184,195,218,246,254,260,293],"interest":[41],"VRDs":[43],"such":[44,59],"as":[45,60],"extracting":[46,55,134],"price":[47,63],"tags":[48,64],"etc.":[52],"However,":[53],"for":[54,65,133,282,313],"semantically":[56],"linked":[57],"entities,":[58,154],"finding":[61],"corresponding":[62],"each":[66],"item,":[67],"these":[68],"either":[70],"limited":[72],"capability":[73],"in":[74,221,243,258,270],"handling":[75],"new":[76,140],"layouts,":[77],"template-based":[79],"approaches,":[80],"or":[81],"require":[82],"extensive":[83],"amounts":[84],"pre-training":[86,131,233],"data":[87,132],"do":[89],"not":[90],"perform":[91],"well,":[92],"deep-learning":[94,239],"approaches.":[95],"In":[96],"this":[97],"work,":[98],"we":[99],"introduce":[100],"a":[101,139,157,182],"program":[102],"synthesis":[103,159],"method,":[104],"namely":[105,207,241],"VRDSynth,":[106,228],"generate":[109],"programs":[110,190],"entity":[113,135,214],"relations":[114,151,167],"multilingual":[116],"VRDs.":[117],"Two":[118],"key":[119],"novelties,":[120],"which":[121],"empower":[122],"VRDSynth":[123,250,275],"tackle":[125],"flexible":[126],"layouts":[127],"while":[128,265,300],"requiring":[129],"no":[130,231],"relations,":[136],"include:":[137],"(1)":[138],"domain-specific":[141],"language":[142],"(DSL)":[143],"effectively":[145],"capture":[146],"the":[147,178,193,212,236,278,306,310],"spatial":[148,166],"textual":[150],"between":[152,168,309],"document":[153],"(2)":[156],"novel":[158],"algorithm":[160],"that":[161,227,292],"makes":[162],"use":[163],"frequent":[165],"construct":[171],"initial":[172],"programs,":[173],"equivalent":[174],"reduction":[175],"prune":[177],"search":[179],"space,":[180],"combination":[183],"positive,":[185],"negative,":[186],"mutually":[188],"exclusive":[189],"improve":[192],"coverage":[194],"programs.":[196],"We":[197],"evaluate":[198],"our":[199],"method":[200],"on":[201,211,263],"two":[202],"popular":[203],"VRD":[204],"understanding":[205],"benchmarks,":[206],"FUNSD":[208,264],"XFUND,":[210],"semantic":[213],"linking":[215],"task,":[216],"consisting":[217],"1,600":[219],"8":[222,247],"different":[223],"languages.":[224,248,272],"Experiments":[225],"show":[226],"despite":[229,305],"having":[230],"prior":[232],"data,":[234],"outperforms":[235],"state-of-the-art":[237],"pre-trained":[238],"approach,":[240],"LayoutXLM,":[242],"5":[244],"out":[245],"Noticeably,":[249],"achieved":[251],"an":[252],"improvement":[253],"42%":[255],"over":[256,286],"LayoutXLM":[257,269,287],"terms":[259],"F1":[261],"score":[262],"being":[266],"complementary":[267],"7/8":[271],"Regarding":[273],"efficiency,":[274],"significantly":[276],"improves":[277],"memory":[279],"footprint":[280],"required":[281,297],"storage":[283],"inference":[285],"(1M":[288],"380MB":[290],"versus":[291],"1.48GB":[294],"3GB":[296],"by":[298],"LayoutXLM),":[299],"maintaining":[301],"similar":[302],"time":[303],"efficiency":[304],"speed":[307],"differences":[308],"languages":[311],"used":[312],"implementation":[314],"(Python":[315],"vs":[316],"C++).":[317]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}