{"id":"https://openalex.org/W4405254931","doi":"https://doi.org/10.1145/3677389.3702542","title":"Retrieval Augmented Generation for Historical Newspapers","display_name":"Retrieval Augmented Generation for Historical Newspapers","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4405254931","doi":"https://doi.org/10.1145/3677389.3702542"},"language":"en","primary_location":{"id":"doi:10.1145/3677389.3702542","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677389.3702542","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677389.3702542?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM/IEEE Joint Conference on Digital Libraries","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/10.1145/3677389.3702542?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006513255","display_name":"Tr\u1ea7n Th\u00e0nh Th\u00e1i","orcid":"https://orcid.org/0000-0002-2866-8913"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"The Trung Tran","raw_affiliation_strings":["University of Science and Technology of Hanoi, Hanoi, Viet Nam"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of Hanoi, Hanoi, Viet Nam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006172563","display_name":"Carlos-Emiliano Gonz\u00e1lez-Gallardo","orcid":"https://orcid.org/0000-0002-0787-2990"},"institutions":[{"id":"https://openalex.org/I4210136805","display_name":"Laboratoire d'Informatique Fondamentale et Appliqu\u00e9e de Tours","ror":"https://ror.org/03r938j26","country_code":"FR","type":"facility","lineage":["https://openalex.org/I110017253","https://openalex.org/I4210136805"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Carlos-Emiliano Gonz\u00e1lez-Gallardo","raw_affiliation_strings":["LIFAT / CESR, University of TOURS, Tours, France"],"affiliations":[{"raw_affiliation_string":"LIFAT / CESR, University of TOURS, Tours, France","institution_ids":["https://openalex.org/I4210136805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033491986","display_name":"Antoine Doucet","orcid":"https://orcid.org/0000-0001-6160-3356"},"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":"Antoine Doucet","raw_affiliation_strings":["University of La Rochelle, La Rochelle, France"],"affiliations":[{"raw_affiliation_string":"University of La Rochelle, La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006513255"],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20419138,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9944000244140625,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.7839992642402649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6756611466407776},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5385926961898804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3400469720363617},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32949307560920715},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.1242157518863678},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.07064566016197205}],"concepts":[{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.7839992642402649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6756611466407776},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5385926961898804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3400469720363617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32949307560920715},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.1242157518863678},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.07064566016197205}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3677389.3702542","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677389.3702542","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677389.3702542?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04796088v1","is_oa":true,"landing_page_url":"https://univ-tours.hal.science/hal-04796088","pdf_url":"https://univ-tours.hal.science/hal-04796088/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL), Dec 2024, Hong Kong, China","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.1145/3677389.3702542","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677389.3702542","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677389.3702542?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405254931.pdf","grobid_xml":"https://content.openalex.org/works/W4405254931.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2202223467","https://openalex.org/W2341986316","https://openalex.org/W3027879771","https://openalex.org/W4239249262","https://openalex.org/W4256250826","https://openalex.org/W4386488973","https://openalex.org/W4402567773"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2376554757","https://openalex.org/W612150824","https://openalex.org/W2361959990","https://openalex.org/W2100945520","https://openalex.org/W1596512750","https://openalex.org/W2383443050","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Nowadays,":[0],"the":[1,13,17,44,84,105,108,168,176,185],"accessibility":[2,81],"and":[3,29,72,89,122,180,190],"long-term":[4],"preservation":[5],"of":[6,19,47,107,130,141,156,167,178,187],"historical":[7,93,132],"records":[8],"are":[9,161],"significantly":[10],"impacted":[11],"by":[12,86],"sharp":[14],"increase":[15],"in":[16,31],"digitization":[18],"these":[20,146],"archives.":[21],"This":[22],"shift":[23],"creates":[24],"new":[25],"opportunities":[26],"for":[27,83],"researchers":[28],"students":[30],"multiple":[32],"disciplines":[33],"to":[34,51,78,125],"broaden":[35],"their":[36],"knowledge":[37,56,123],"or":[38],"conduct":[39],"multidisciplinary":[40],"research.":[41],"However,":[42,92],"given":[43],"vast":[45],"amount":[46],"data":[48],"that":[49,112,143,172],"needs":[50],"be":[52],"analyzed,":[53],"using":[54],"this":[55,80,101,164],"is":[57,97],"not":[58],"easy.":[59],"Different":[60],"natural":[61],"language":[62,115],"processing":[63],"tasks":[64],"such":[65],"as":[66],"named":[67],"entity":[68,70],"recognition,":[69],"linking,":[71],"article":[73,95],"separation":[74],"have":[75],"been":[76],"developed":[77],"make":[79],"easier":[82],"public":[85],"extracting":[87],"information":[88,182],"structuring":[90],"data.":[91],"newspaper":[94,133],"aggregation":[96],"still":[98],"unexplored.":[99],"In":[100,135],"work,":[102],"we":[103,137],"demonstrate":[104],"potential":[106],"retrieval-augmented":[109],"generation":[110],"framework":[111],"integrates":[113],"large":[114],"models":[116],"(LLMs),":[117],"a":[118,127,139],"semantic":[119,173],"retrieval":[120,174],"module,":[121],"bases":[124],"create":[126],"system":[128],"capable":[129],"aggregating":[131],"articles.":[134],"addition,":[136],"propose":[138],"set":[140],"metrics":[142],"permit":[144],"evaluating":[145],"generative":[147],"systems":[148],"without":[149],"requiring":[150],"any":[151],"ground":[152],"truth.":[153],"The":[154],"results":[155],"our":[157],"proposed":[158],"RAG":[159],"pipeline":[160],"promising":[162],"at":[163],"early":[165],"stage":[166],"system.":[169],"They":[170],"show":[171],"with":[175],"help":[177],"reranking":[179],"additional":[181],"(NER)":[183],"reduces":[184],"impact":[186],"OCR":[188],"errors":[189],"query":[191],"misspellings.":[192]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
