{"id":"https://openalex.org/W7118213915","doi":"https://doi.org/10.1109/aiccsa66935.2025.11315207","title":"A Distributed RAG-based Framework for Automated Extraction of Information from Multiple Types of Resources","display_name":"A Distributed RAG-based Framework for Automated Extraction of Information from Multiple Types of Resources","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7118213915","doi":"https://doi.org/10.1109/aiccsa66935.2025.11315207"},"language":null,"primary_location":{"id":"doi:10.1109/aiccsa66935.2025.11315207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa66935.2025.11315207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088184165","display_name":"Charbel El Gemayel","orcid":null},"institutions":[{"id":"https://openalex.org/I20307877","display_name":"Antonine University","ror":"https://ror.org/03gc39678","country_code":"LB","type":"education","lineage":["https://openalex.org/I20307877"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Charbel El Gemayel","raw_affiliation_strings":["Antonine University,TICKET Lab, Technology in Computer Sciences department,Hadat-Baabda,Lebanon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Antonine University,TICKET Lab, Technology in Computer Sciences department,Hadat-Baabda,Lebanon","institution_ids":["https://openalex.org/I20307877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111809199","display_name":"Joseph El Gemayel","orcid":null},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joseph El Gemayel","raw_affiliation_strings":["University of Strathclyde,Computer & Information Sciences,Glasgow,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Strathclyde,Computer & Information Sciences,Glasgow,United Kingdom","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039463595","display_name":"Joseph Constantin","orcid":"https://orcid.org/0000-0002-7911-1218"},"institutions":[{"id":"https://openalex.org/I160368002","display_name":"Lebanese University","ror":"https://ror.org/05x6qnc69","country_code":"LB","type":"education","lineage":["https://openalex.org/I160368002"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Joseph Constantin","raw_affiliation_strings":["Lebanese University,LaRRIS Laboratory,Fanar,Lebanon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lebanese University,LaRRIS Laboratory,Fanar,Lebanon","institution_ids":["https://openalex.org/I160368002"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.71649954,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.2531000077724457,"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":0.2531000077724457,"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":0.14309999346733093,"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/T10028","display_name":"Topic Modeling","score":0.07039999961853027,"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/structuring","display_name":"Structuring","score":0.6017000079154968},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5692999958992004},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5649999976158142},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.48570001125335693},{"id":"https://openalex.org/keywords/credibility","display_name":"Credibility","score":0.4643000066280365},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4327999949455261},{"id":"https://openalex.org/keywords/information-integration","display_name":"Information integration","score":0.3587000072002411}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8312000036239624},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.6017000079154968},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5692999958992004},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5649999976158142},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.48570001125335693},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4674000144004822},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aiccsa66935.2025.11315207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa66935.2025.11315207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accessing":[0],"authoritative":[1],"information":[2,51,80],"in":[3,108],"areas":[4],"such":[5,84],"as":[6,85],"healthcare,":[7],"cybersecurity,":[8],"and":[9,22,52,77,90,98,121,129,143],"artificial":[10],"intelligence":[11],"remains":[12],"a":[13,64],"challenge":[14],"due":[15],"to":[16,73,119,137],"the":[17,23,29,48,75,102,134],"heterogeneity":[18],"of":[19,26,32,50,54,79,104],"data":[20,96,106,139],"sources":[21],"varying":[24],"credibility":[25],"content.":[27],"With":[28],"increasing":[30],"integration":[31],"advanced":[33],"technologies":[34],"into":[35],"daily":[36],"life,":[37],"there":[38],"is":[39,99],"an":[40],"urgent":[41],"need":[42],"for":[43,101],"systems":[44],"that":[45,71],"can":[46],"streamline":[47],"retrieval":[49],"extraction":[53,76],"knowledge":[55,147],"from":[56,81,125],"different":[57],"formats.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,116],"present":[63],"distributed,":[65],"Retrieval-Augmented":[66],"Generation":[67],"(RAG)":[68],"based":[69],"framework":[70,93],"aims":[72],"automate":[74],"structuring":[78],"multimodal":[82],"resources,":[83],"websites,":[86],"PDFs,":[87],"images,":[88],"audio,":[89],"video.":[91],"The":[92],"supports":[94],"real-time":[95],"processing":[97],"optimized":[100],"creation":[103],"open":[105],"sets":[107],"any":[109],"subject":[110],"area.":[111],"To":[112],"validate":[113],"our":[114],"approach,":[115],"applied":[117],"it":[118],"cigars":[120],"beverages,":[122],"using":[123],"content":[124],"online":[126],"articles,":[127],"reviews,":[128],"posts.":[130],"Our":[131],"results":[132],"show":[133],"framework\u2019s":[135],"potential":[136],"simplify":[138],"integration,":[140],"improve":[141],"usability":[142],"enable":[144],"scalable,":[145],"contextual":[146],"generation.":[148]},"counts_by_year":[],"updated_date":"2026-01-08T20:05:33.558190","created_date":"2026-01-05T00:00:00"}