{"id":"https://openalex.org/W4410826117","doi":"https://doi.org/10.1007/s10032-025-00531-z","title":"The PARES Database: Information Extraction over Historical Parish Records","display_name":"The PARES Database: Information Extraction over Historical Parish Records","publication_year":2025,"publication_date":"2025-05-28","ids":{"openalex":"https://openalex.org/W4410826117","doi":"https://doi.org/10.1007/s10032-025-00531-z"},"language":"en","primary_location":{"id":"doi:10.1007/s10032-025-00531-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-025-00531-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00531-z.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00531-z.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062928201","display_name":"Jos\u00e9 Onofre Montesa Andr\u00e9s","orcid":"https://orcid.org/0000-0002-5541-8231"},"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":"Jos\u00e9 Andr\u00e9s","raw_affiliation_strings":["PRHLT Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","tranSkriptorium AI, Valencia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PRHLT Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]},{"raw_affiliation_string":"tranSkriptorium AI, Valencia, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113165084","display_name":"C. Edward Wall","orcid":null},"institutions":[{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Casey Wall","raw_affiliation_strings":["Laboratoire L3i, Universit\u00e9 de La Rochelle, La Rochelle, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire L3i, Universit\u00e9 de La Rochelle, La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078741085","display_name":"Sol\u00e8ne Tarride","orcid":"https://orcid.org/0000-0001-6174-9865"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sol\u00e8ne Tarride","raw_affiliation_strings":["TEKLIA, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TEKLIA, Paris, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063992777","display_name":"Micka\u00ebl Coustaty","orcid":"https://orcid.org/0000-0002-0123-439X"},"institutions":[{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Micka\u00ebl Coustaty","raw_affiliation_strings":["Laboratoire L3i, Universit\u00e9 de La Rochelle, La Rochelle, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire L3i, Universit\u00e9 de La Rochelle, La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016214452","display_name":"Alejandro H. Toselli","orcid":"https://orcid.org/0000-0001-6955-9249"},"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":"Alejandro H. Toselli","raw_affiliation_strings":["PRHLT Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","tranSkriptorium AI, Valencia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PRHLT Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]},{"raw_affiliation_string":"tranSkriptorium AI, Valencia, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073107684","display_name":"Enrique Vidal","orcid":"https://orcid.org/0000-0003-4579-5196"},"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":"Enrique Vidal","raw_affiliation_strings":["PRHLT Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","tranSkriptorium AI, Valencia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PRHLT Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]},{"raw_affiliation_string":"tranSkriptorium AI, Valencia, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062928201","https://openalex.org/A5113165084"],"corresponding_institution_ids":["https://openalex.org/I60053951","https://openalex.org/I78744979"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15391379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":"3","first_page":"377","last_page":"389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.8773999810218811,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.8773999810218811,"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":0.7896000146865845,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.7509999871253967,"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/genealogy","display_name":"Genealogy","score":0.5248579978942871},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4369889795780182},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4221121370792389},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4200414717197418},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.3691360652446747},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.3556970953941345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.32498830556869507},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.1448768675327301},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.1106480062007904},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.03870227932929993}],"concepts":[{"id":"https://openalex.org/C53553401","wikidata":"https://www.wikidata.org/wiki/Q47307","display_name":"Genealogy","level":1,"score":0.5248579978942871},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4369889795780182},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4221121370792389},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4200414717197418},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.3691360652446747},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.3556970953941345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32498830556869507},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.1448768675327301},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1106480062007904},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.03870227932929993}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10032-025-00531-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-025-00531-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00531-z.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-05319085v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05319085","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal on Document Analysis and Recognition, 2025, 28 (3), pp.377-389. &#x27E8;10.1007/s10032-025-00531-z&#x27E9;","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:riunet.upv.es:10251/232650","is_oa":true,"landing_page_url":"https://riunet.upv.es/handle/10251/232650","pdf_url":null,"source":{"id":"https://openalex.org/S4306400639","display_name":"RiuNet (Universitat Polit\u00e8cnica de Val\u00e8ncia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10032-025-00531-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-025-00531-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00531-z.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1490602166","display_name":"Artificial Intelligence for the study if Charleville, R\u00e9 (Island), Tous and INED demographic data","funder_award_id":"ANR-23-CE38-0016","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320334905","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410826117.pdf","grobid_xml":"https://content.openalex.org/works/W4410826117.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1934041838","https://openalex.org/W2107223151","https://openalex.org/W2127141656","https://openalex.org/W2315885287","https://openalex.org/W2785820430","https://openalex.org/W2786974559","https://openalex.org/W2963150697","https://openalex.org/W2963828007","https://openalex.org/W3004042913","https://openalex.org/W3004293532","https://openalex.org/W3153030012","https://openalex.org/W3184971748","https://openalex.org/W3198746778","https://openalex.org/W4214671568","https://openalex.org/W4281390395","https://openalex.org/W4283276297","https://openalex.org/W4312351788","https://openalex.org/W4315884068","https://openalex.org/W4380149085","https://openalex.org/W4385990901","https://openalex.org/W4385991039","https://openalex.org/W4389150735","https://openalex.org/W4390384657","https://openalex.org/W4393546676","https://openalex.org/W4393737115","https://openalex.org/W4393761179","https://openalex.org/W4394035948","https://openalex.org/W4396820396","https://openalex.org/W4400613392","https://openalex.org/W4402343048","https://openalex.org/W4402397445"],"related_works":["https://openalex.org/W2003932708","https://openalex.org/W1967424056","https://openalex.org/W2284877871","https://openalex.org/W2138102289","https://openalex.org/W868043274","https://openalex.org/W2513523087","https://openalex.org/W1187916458","https://openalex.org/W2373861055","https://openalex.org/W1559716973","https://openalex.org/W3109364360"],"abstract_inverted_index":{"Abstract":[0],"Historical":[1],"census":[2,59],"records":[3],"convey":[4],"information":[5,39,75,104,125],"that":[6,25,33,101],"is":[7,28],"key":[8],"to":[9,30],"perform":[10],"genealogical":[11],"research":[12,31],"and":[13],"demographic":[14],"studies.":[15],"Given":[16],"the":[17,35,106,116,124],"large":[18],"number":[19],"of":[20,22,38,43,53,118],"documents":[21],"this":[23,41,46,54,65],"type":[24,42],"exist,":[26],"it":[27],"crucial":[29],"methods":[32,73,80],"allow":[34],"automatic":[36],"extraction":[37,126],"from":[40,61,105],"document.":[44],"In":[45],"work,":[47],"we":[48,67],"present":[49],"a":[50,82],"new":[51],"corpus":[52],"kind,":[55],"comprising":[56],"535":[57],"historical":[58],"tables":[60],"French":[62],"archives.":[63],"Alongside":[64],"dataset,":[66],"have":[68],"assessed":[69],"three":[70,120],"different":[71],"baseline":[72,96],"for":[74],"extraction.":[76],"The":[77,94],"first":[78],"two":[79],"employ":[81],"traditional":[83],"sequential":[84],"approach,":[85],"where":[86],"table":[87,107],"rows":[88],"are":[89],"detected":[90],"before":[91],"extracting":[92],"information.":[93],"third":[95],"uses":[97],"an":[98],"end-to-end":[99],"model":[100],"directly":[102],"extracts":[103],"images":[108],"without":[109],"prior":[110],"row":[111],"detection.":[112],"Our":[113],"results":[114],"demonstrate":[115],"effectiveness":[117],"all":[119],"baselines":[121],"in":[122],"tackling":[123],"task.":[127]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
