{"id":"https://openalex.org/W7162395179","doi":"https://doi.org/10.5220/0014975500004018","title":"A Workflow for Structured Information Extraction from Public-Sector PDF Documents Using a Small Language Model","display_name":"A Workflow for Structured Information Extraction from Public-Sector PDF Documents Using a Small Language Model","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7162395179","doi":"https://doi.org/10.5220/0014975500004018"},"language":null,"primary_location":{"id":"doi:10.5220/0014975500004018","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0014975500004018","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0014975500004018","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119547371","display_name":"Thais de Sousa","orcid":null},"institutions":[{"id":"https://openalex.org/I243754102","display_name":"Universidade Federal do Cear\u00e1","ror":"https://ror.org/03srtnf24","country_code":"BR","type":"education","lineage":["https://openalex.org/I243754102"]},{"id":"https://openalex.org/I3125581668","display_name":"Universidade de Fortaleza","ror":"https://ror.org/02ynbzc81","country_code":"BR","type":"education","lineage":["https://openalex.org/I3125581668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Tha\u00eds de Sousa","raw_affiliation_strings":["Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I243754102"]},{"raw_affiliation_string":"Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I3125581668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137020025","display_name":"Paulo Fabr\u00edcio","orcid":null},"institutions":[{"id":"https://openalex.org/I243754102","display_name":"Universidade Federal do Cear\u00e1","ror":"https://ror.org/03srtnf24","country_code":"BR","type":"education","lineage":["https://openalex.org/I243754102"]},{"id":"https://openalex.org/I3125581668","display_name":"Universidade de Fortaleza","ror":"https://ror.org/02ynbzc81","country_code":"BR","type":"education","lineage":["https://openalex.org/I3125581668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Paulo Fabr\u00edcio","raw_affiliation_strings":["Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I243754102"]},{"raw_affiliation_string":"Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I3125581668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137046444","display_name":"Paulo Lima","orcid":null},"institutions":[{"id":"https://openalex.org/I243754102","display_name":"Universidade Federal do Cear\u00e1","ror":"https://ror.org/03srtnf24","country_code":"BR","type":"education","lineage":["https://openalex.org/I243754102"]},{"id":"https://openalex.org/I3125581668","display_name":"Universidade de Fortaleza","ror":"https://ror.org/02ynbzc81","country_code":"BR","type":"education","lineage":["https://openalex.org/I3125581668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Paulo Lima","raw_affiliation_strings":["Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I243754102"]},{"raw_affiliation_string":"Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I3125581668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136995053","display_name":"Jo\u00e3o Braga","orcid":null},"institutions":[{"id":"https://openalex.org/I243754102","display_name":"Universidade Federal do Cear\u00e1","ror":"https://ror.org/03srtnf24","country_code":"BR","type":"education","lineage":["https://openalex.org/I243754102"]},{"id":"https://openalex.org/I3125581668","display_name":"Universidade de Fortaleza","ror":"https://ror.org/02ynbzc81","country_code":"BR","type":"education","lineage":["https://openalex.org/I3125581668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Braga","raw_affiliation_strings":["Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I243754102"]},{"raw_affiliation_string":"Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I3125581668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137029429","display_name":"Rafael Pereira","orcid":null},"institutions":[{"id":"https://openalex.org/I243754102","display_name":"Universidade Federal do Cear\u00e1","ror":"https://ror.org/03srtnf24","country_code":"BR","type":"education","lineage":["https://openalex.org/I243754102"]},{"id":"https://openalex.org/I3125581668","display_name":"Universidade de Fortaleza","ror":"https://ror.org/02ynbzc81","country_code":"BR","type":"education","lineage":["https://openalex.org/I3125581668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rafael Pereira","raw_affiliation_strings":["Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I243754102"]},{"raw_affiliation_string":"Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I3125581668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137028815","display_name":"Tales Nogueira","orcid":null},"institutions":[{"id":"https://openalex.org/I3125581668","display_name":"Universidade de Fortaleza","ror":"https://ror.org/02ynbzc81","country_code":"BR","type":"education","lineage":["https://openalex.org/I3125581668"]},{"id":"https://openalex.org/I3130695932","display_name":"University for International Integration of the Afro-Brazilian Lusophony","ror":"https://ror.org/02p928v94","country_code":"BR","type":"education","lineage":["https://openalex.org/I3130695932"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Tales Nogueira","raw_affiliation_strings":["Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil","University of the International Integration of the Afro-Brazilian Lusophony, Reden\u00e7\u00e3o\u2013CE, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I3125581668"]},{"raw_affiliation_string":"University of the International Integration of the Afro-Brazilian Lusophony, Reden\u00e7\u00e3o\u2013CE, Brazil","institution_ids":["https://openalex.org/I3130695932"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137037990","display_name":"Wendley da Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I243754102","display_name":"Universidade Federal do Cear\u00e1","ror":"https://ror.org/03srtnf24","country_code":"BR","type":"education","lineage":["https://openalex.org/I243754102"]},{"id":"https://openalex.org/I3018325552","display_name":"Instituto Federal de Educa\u00e7\u00e3o, Ci\u00eancia e Tecnologia do Cear\u00e1","ror":"https://ror.org/02225fd27","country_code":"BR","type":"government","lineage":["https://openalex.org/I3018325552"]},{"id":"https://openalex.org/I3125581668","display_name":"Universidade de Fortaleza","ror":"https://ror.org/02ynbzc81","country_code":"BR","type":"education","lineage":["https://openalex.org/I3125581668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Wendley da Silva","raw_affiliation_strings":["Federal University of Cear\u00e1, Sobral\u2013CE, Brazil","Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Cear\u00e1, Sobral\u2013CE, Brazil","institution_ids":["https://openalex.org/I243754102","https://openalex.org/I3018325552"]},{"raw_affiliation_string":"Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I3125581668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137034761","display_name":"Antonia da Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I243754102","display_name":"Universidade Federal do Cear\u00e1","ror":"https://ror.org/03srtnf24","country_code":"BR","type":"education","lineage":["https://openalex.org/I243754102"]},{"id":"https://openalex.org/I3125581668","display_name":"Universidade de Fortaleza","ror":"https://ror.org/02ynbzc81","country_code":"BR","type":"education","lineage":["https://openalex.org/I3125581668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Antonia da Silva","raw_affiliation_strings":["Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I243754102"]},{"raw_affiliation_string":"Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I3125581668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137068392","display_name":"Rossana Andrade","orcid":null},"institutions":[{"id":"https://openalex.org/I243754102","display_name":"Universidade Federal do Cear\u00e1","ror":"https://ror.org/03srtnf24","country_code":"BR","type":"education","lineage":["https://openalex.org/I243754102"]},{"id":"https://openalex.org/I3125581668","display_name":"Universidade de Fortaleza","ror":"https://ror.org/02ynbzc81","country_code":"BR","type":"education","lineage":["https://openalex.org/I3125581668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rossana Andrade","raw_affiliation_strings":["Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Cear\u00e1, Campus do Pici, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I243754102"]},{"raw_affiliation_string":"Group of Computer Networks, Software Engineering and Systems, Fortaleza\u2013CE, Brazil","institution_ids":["https://openalex.org/I3125581668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092574183","display_name":"Alexandre Cialdini","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136275","display_name":"Secretaria da Sa\u00fade","ror":"https://ror.org/03afd8w19","country_code":"BR","type":"government","lineage":["https://openalex.org/I4210136275"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alexandre Cialdini","raw_affiliation_strings":["Secretariat of Planning and Management of Cear\u00e1, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Secretariat of Planning and Management of Cear\u00e1, Brazil","institution_ids":["https://openalex.org/I4210136275"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61827152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"719","last_page":"730"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.23149999976158142,"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":0.23149999976158142,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.18050000071525574,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.06719999760389328,"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/information-extraction","display_name":"Information extraction","score":0.6007999777793884},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5583999752998352},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.36800000071525574},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3271999955177307},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3264000117778778},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3057999908924103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437000274658203},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6007999777793884},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5583999752998352},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46700000762939453},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.352400004863739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3522999882698059},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32120001316070557},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C21338462","wikidata":"https://www.wikidata.org/wiki/Q1662581","display_name":"Information model","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0014975500004018","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0014975500004018","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0014975500004018","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0014975500004018","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-27T00:00:00"}
