{"id":"https://openalex.org/W4417358451","doi":"https://doi.org/10.3390/make7040167","title":"Receipt Information Extraction with Joint Multi-Modal Transformer and Rule-Based Model","display_name":"Receipt Information Extraction with Joint Multi-Modal Transformer and Rule-Based Model","publication_year":2025,"publication_date":"2025-12-16","ids":{"openalex":"https://openalex.org/W4417358451","doi":"https://doi.org/10.3390/make7040167"},"language":"en","primary_location":{"id":"doi:10.3390/make7040167","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7040167","pdf_url":"https://www.mdpi.com/2504-4990/7/4/167/pdf?version=1765874282","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/7/4/167/pdf?version=1765874282","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028560978","display_name":"Xandru Mifsud","orcid":"https://orcid.org/0000-0002-4391-2988"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":false,"raw_author_name":"Xandru Mifsud","raw_affiliation_strings":["Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta","institution_ids":["https://openalex.org/I197854408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084669359","display_name":"Leander Grech","orcid":"https://orcid.org/0000-0002-4062-0787"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":false,"raw_author_name":"Leander Grech","raw_affiliation_strings":["Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta","institution_ids":["https://openalex.org/I197854408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120814963","display_name":"Adriana Baldacchino","orcid":"https://orcid.org/0009-0001-5602-0874"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":false,"raw_author_name":"Adriana Baldacchino","raw_affiliation_strings":["Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta","institution_ids":["https://openalex.org/I197854408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120814964","display_name":"L\u00e9a Keller","orcid":"https://orcid.org/0009-0005-2391-3026"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":false,"raw_author_name":"L\u00e9a Keller","raw_affiliation_strings":["Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta","institution_ids":["https://openalex.org/I197854408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017433512","display_name":"Gianluca Valentino","orcid":"https://orcid.org/0000-0003-3864-7785"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":true,"raw_author_name":"Gianluca Valentino","raw_affiliation_strings":["Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta","institution_ids":["https://openalex.org/I197854408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052348633","display_name":"Adrian Muscat","orcid":"https://orcid.org/0000-0002-9157-2818"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":true,"raw_author_name":"Adrian Muscat","raw_affiliation_strings":["Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta","institution_ids":["https://openalex.org/I197854408"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5017433512","https://openalex.org/A5052348633"],"corresponding_institution_ids":["https://openalex.org/I197854408"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4268364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"4","first_page":"167","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9764999747276306,"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":0.9764999747276306,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.014700000174343586,"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":0.000699999975040555,"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/classifier","display_name":"Classifier (UML)","score":0.6409000158309937},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6121000051498413},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.4991999864578247},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.46779999136924744},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45509999990463257},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42640000581741333},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.34310001134872437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271999716758728},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6409000158309937},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6121000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5572999715805054},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.4991999864578247},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.46779999136924744},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4262999892234802},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27570000290870667}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/make7040167","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7040167","pdf_url":"https://www.mdpi.com/2504-4990/7/4/167/pdf?version=1765874282","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2af5703c96e34b14bce13794eb0afabf","is_oa":true,"landing_page_url":"https://doaj.org/article/2af5703c96e34b14bce13794eb0afabf","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction, Vol 7, Iss 4, p 167 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/make7040167","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7040167","pdf_url":"https://www.mdpi.com/2504-4990/7/4/167/pdf?version=1765874282","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321039","display_name":"Malta Council for Science and Technology","ror":"https://ror.org/05qk3dq04"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417358451.pdf","grobid_xml":"https://content.openalex.org/works/W4417358451.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2144554289","https://openalex.org/W2194187530","https://openalex.org/W2605982830","https://openalex.org/W2777652944","https://openalex.org/W2784050770","https://openalex.org/W2963687456","https://openalex.org/W2982618994","https://openalex.org/W2997154779","https://openalex.org/W3003484198","https://openalex.org/W3082397598","https://openalex.org/W3138516171","https://openalex.org/W3203431461","https://openalex.org/W3204562006","https://openalex.org/W4225683503","https://openalex.org/W4304013646","https://openalex.org/W4312230431","https://openalex.org/W4312233877","https://openalex.org/W4313163001","https://openalex.org/W4321021053","https://openalex.org/W4383113591","https://openalex.org/W4384891056","https://openalex.org/W4385988828","https://openalex.org/W4402418504","https://openalex.org/W4406106184","https://openalex.org/W4409729633"],"related_works":[],"abstract_inverted_index":{"A":[0,124],"receipt":[1,12],"information":[2],"extraction":[3],"task":[4],"requires":[5],"both":[6],"textual":[7,182,268],"and":[8,36,51,66,79,105,109,130,192,205,216,231,239,250],"spatial":[9,41,224],"analyses.":[10],"Early":[11],"analysis":[13],"systems":[14],"primarily":[15],"relied":[16],"on":[17,96,121,213,236],"template":[18],"matching":[19],"to":[20,57,84,149,160],"extract":[21],"data":[22,183],"from":[23,273],"spatially":[24],"structured":[25],"documents.":[26],"However,":[27],"these":[28],"methods":[29,196,220],"lack":[30],"generalizability":[31],"across":[32],"various":[33],"document":[34,45,64],"layouts":[35],"require":[37],"defining":[38],"the":[39,97,119,161,199,247,251,257],"specific":[40],"characteristics":[42],"of":[43,49,76,100,207,246,253,264],"unseen":[44,63],"sources.":[46],"The":[47,139,164,195],"advent":[48],"convolutional":[50],"recurrent":[52],"neural":[53,102],"networks":[54],"has":[55],"led":[56,83],"models":[58],"that":[59],"generalize":[60],"better":[61],"over":[62],"layouts,":[65],"more":[67,87],"recently,":[68],"multi-modal":[69,103],"transformer-based":[70,168],"models,":[71],"which":[72,177],"consider":[73],"a":[74,101,106,173,254],"combination":[75,113],"text,":[77],"visual,":[78],"layout":[80],"inputs,":[81],"have":[82],"an":[85,156,260],"even":[86],"significant":[88],"boost":[89],"in":[90,198,266],"document-understanding":[91],"capabilities.":[92],"This":[93],"work":[94],"focuses":[95],"joint":[98],"use":[99],"transformer":[104,120],"rule-based":[107,200,255],"model":[108,145,169,175,201],"studies":[110],"whether":[111],"this":[112,137],"achieves":[114],"higher":[115],"performance":[116],"levels":[117],"than":[118],"its":[122],"own.":[123],"comprehensively":[125],"annotated":[126],"dataset,":[127],"comprising":[128],"real-world":[129],"synthetic":[131],"receipts,":[132],"was":[133,147,170,178],"specifically":[134],"developed":[135],"for":[136,180,221],"study.":[138],"open":[140],"source":[141],"optical":[142],"character":[143],"recognition":[144],"DocTR":[146],"used":[148],"textually":[150],"scan":[151],"receipts":[152],"and,":[153],"together":[154],"with":[155,172],"image,":[157],"provided":[158],"input":[159],"classifier":[162,174,248],"model.":[163],"open-source":[165],"pre-trained":[166],"LayoutLMv3":[167],"augmented":[171],"head,":[176],"trained":[179],"classifying":[181,267],"into":[184],"12":[185],"predefined":[186],"labels,":[187],"such":[188],"as":[189],"date,":[190],"price,":[191],"shop":[193],"name.":[194],"implemented":[197],"were":[202],"manually":[203],"designed":[204],"consisted":[206],"four":[208],"types:":[209],"pattern-matching":[210],"rules":[211],"based":[212,235],"regular":[214],"expressions":[215],"logic,":[217],"database":[218],"search-based":[219],"named":[222],"entities,":[223],"pattern":[225],"discovery":[226],"guided":[227],"by":[228],"statistical":[229],"metrics,":[230],"error":[232],"correcting":[233],"mechanisms":[234],"confidence":[237],"scores":[238],"local":[240],"distance":[241],"metrics.":[242],"Following":[243],"hyperparameter":[244],"tuning":[245],"head":[249],"integration":[252],"model,":[256],"system":[258],"achieved":[259],"overall":[261],"F1":[262],"score":[263],"0.98":[265],"data,":[269],"including":[270],"line":[271],"items,":[272],"receipts.":[274]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-12-16T00:00:00"}