{"id":"https://openalex.org/W4413757356","doi":"https://doi.org/10.1145/3704268.3742699","title":"Improving Lightweight Named Entity Recognition in Handwritten Documents by Predicting Pyramidal Histograms of Characters","display_name":"Improving Lightweight Named Entity Recognition in Handwritten Documents by Predicting Pyramidal Histograms of Characters","publication_year":2025,"publication_date":"2025-08-27","ids":{"openalex":"https://openalex.org/W4413757356","doi":"https://doi.org/10.1145/3704268.3742699"},"language":"en","primary_location":{"id":"doi:10.1145/3704268.3742699","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3742699","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3742699","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3742699","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092312031","display_name":"David Villanova-Aparisi","orcid":"https://orcid.org/0000-0003-2301-6673"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"David Villanova-Aparisi","raw_affiliation_strings":["PRHLT Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"PRHLT Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078731198","display_name":"Carlos-D. Mart\u00ednez-Hinarejos","orcid":"https://orcid.org/0000-0002-6139-2891"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos D. Mart\u00ednez-Hinarejos","raw_affiliation_strings":["PRHLT Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"PRHLT Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044640092","display_name":"Ver\u00f3nica Romero","orcid":"https://orcid.org/0000-0002-1721-5732"},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ver\u00f3nica Romero","raw_affiliation_strings":["Departament d'Inform\u00e0tica, Universitat de Val\u00e8ncia, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Departament d'Inform\u00e0tica, Universitat de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I16097986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092312032","display_name":"Mois\u00e9s Pastor-Gadea","orcid":"https://orcid.org/0000-0002-1833-7440"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mois\u00e9s Pastor-Gadea","raw_affiliation_strings":["PRHLT Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"PRHLT Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5092312031"],"corresponding_institution_ids":["https://openalex.org/I60053951"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13010912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9987000226974487,"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":0.7751254439353943},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.699899435043335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6675528883934021},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6143031716346741},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.398414671421051},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3384280800819397},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3233884572982788},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17535239458084106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751254439353943},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.699899435043335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6675528883934021},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6143031716346741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.398414671421051},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3384280800819397},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3233884572982788},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17535239458084106}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3704268.3742699","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3742699","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3742699","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3704268.3742699","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3742699","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3742699","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4267046068","display_name":null,"funder_award_id":"CIBEFP/2023/170 and ACIF/2021/436","funder_id":"https://openalex.org/F4320321864","funder_display_name":"Generalitat Valenciana"}],"funders":[{"id":"https://openalex.org/F4320321864","display_name":"Generalitat Valenciana","ror":"https://ror.org/0097mvx21"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413757356.pdf","grobid_xml":"https://content.openalex.org/works/W4413757356.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1934041838","https://openalex.org/W1970026646","https://openalex.org/W2008274828","https://openalex.org/W2127141656","https://openalex.org/W2131774270","https://openalex.org/W2141356776","https://openalex.org/W2152928267","https://openalex.org/W2163107094","https://openalex.org/W2296283641","https://openalex.org/W2442408233","https://openalex.org/W2579755192","https://openalex.org/W2785887616","https://openalex.org/W2786974559","https://openalex.org/W2889198729","https://openalex.org/W2889436406","https://openalex.org/W2914417638","https://openalex.org/W2946759265","https://openalex.org/W2952594430","https://openalex.org/W2962822108","https://openalex.org/W2963037989","https://openalex.org/W2963271566","https://openalex.org/W2963341956","https://openalex.org/W2970730153","https://openalex.org/W3023337184","https://openalex.org/W3034328552","https://openalex.org/W3083876082","https://openalex.org/W3115058362","https://openalex.org/W3117568220","https://openalex.org/W3176512504","https://openalex.org/W3198675293","https://openalex.org/W3199662997","https://openalex.org/W4281633829","https://openalex.org/W4281665026","https://openalex.org/W4283276297","https://openalex.org/W4283361265","https://openalex.org/W4285124838","https://openalex.org/W4315884068","https://openalex.org/W4318207145","https://openalex.org/W4320481960","https://openalex.org/W4360841345","https://openalex.org/W4382202677","https://openalex.org/W4385990880","https://openalex.org/W4385990953","https://openalex.org/W4385991039","https://openalex.org/W4386008045","https://openalex.org/W4386017236","https://openalex.org/W4390670543","https://openalex.org/W4393272863","https://openalex.org/W4396820396","https://openalex.org/W4402135494","https://openalex.org/W4402135609","https://openalex.org/W4402343056","https://openalex.org/W4402396652","https://openalex.org/W4406196974"],"related_works":["https://openalex.org/W2107628111","https://openalex.org/W2394004323","https://openalex.org/W2398764543","https://openalex.org/W2789802309","https://openalex.org/W2027335291","https://openalex.org/W4210328553","https://openalex.org/W1980417906","https://openalex.org/W2171903035","https://openalex.org/W2106598802","https://openalex.org/W2123241129"],"abstract_inverted_index":{"Named":[0],"Entity":[1],"Recogniton":[2],"(NER)":[3],"consists":[4],"of":[5,8,85,89,105,111,118,154,165],"tagging":[6,41,68,147],"parts":[7],"an":[9,57],"unstructured":[10],"text":[11],"containing":[12],"particular":[13],"semantic":[14],"information.":[15],"When":[16],"applied":[17],"to":[18,24,40,50,62,121],"handwritten":[19],"documents,":[20],"it":[21,26,46],"is":[22,37,47],"possible":[23,49],"do":[25,51],"as":[27],"a":[28,93],"two-step":[29],"approach":[30,79],"in":[31,92,143],"which":[32],"Handwritten":[33],"Text":[34],"Recognition":[35],"(HTR)":[36],"performed":[38],"prior":[39],"the":[42,64,67,77,82,102,116,123,132,151,155,162,166],"automatic":[43],"transcription.":[44],"However,":[45],"also":[48,114],"both":[52,144],"tasks":[53],"simultaneously":[54],"by":[55,80,130],"using":[56],"HTR":[58],"model":[59,160],"that":[60,107,129],"learns":[61],"output":[63],"transcription":[65,145],"and":[66,146],"symbols.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73,113],"focus":[74],"on":[75,135],"improving":[76],"one-step":[78],"introducing":[81],"auxiliary":[83],"task":[84],"predicting":[86],"Pyramidal":[87],"Histograms":[88],"Characters":[90],"(PHOC)":[91],"Convolutional":[94],"Recurrent":[95],"Neural":[96],"Network":[97],"(CRNN)":[98],"model.":[99],"Moreover,":[100],"given":[101],"recent":[103],"rise":[104],"models":[106],"digest":[108],"large":[109],"amounts":[110],"data,":[112],"study":[115],"usage":[117],"synthetic":[119,136],"data":[120,137],"pretrain":[122],"proposed":[124],"architecture.":[125],"Our":[126],"experiments":[127],"show":[128],"pretraining":[131],"PHOC-based":[133],"architecture":[134],"substantial":[138],"improvements":[139],"can":[140],"be":[141],"made":[142],"quality":[148],"without":[149],"compromising":[150],"computational":[152],"cost":[153],"decoding":[156],"step.":[157],"The":[158],"resulting":[159],"matches":[161],"NER":[163],"performance":[164],"state-of-the-art":[167],"while":[168],"keeping":[169],"its":[170],"lightweight":[171],"nature.":[172]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}