{"id":"https://openalex.org/W7140105006","doi":"https://doi.org/10.18653/v1/2026.latechclfl-1.23","title":"How to Efficiently Explore Noisy Historical Data? Leveraging Corpus Pre-Targeting to Enhance Graph-based RAG","display_name":"How to Efficiently Explore Noisy Historical Data? Leveraging Corpus Pre-Targeting to Enhance Graph-based RAG","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140105006","doi":"https://doi.org/10.18653/v1/2026.latechclfl-1.23"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.latechclfl-1.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.23","pdf_url":"https://aclanthology.org/2026.latechclfl-1.23.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.latechclfl-1.23.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099068934","display_name":"Donghan Bian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100316","display_name":"\u00c9cole Nationale des Chartes","ror":"https://ror.org/013xvg556","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580","https://openalex.org/I4210100316"]},{"id":"https://openalex.org/I4210138808","display_name":"\u00c9cole Pour l'Informatique et les Techniques Avanc\u00e9es","ror":"https://ror.org/04r5ddq29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210138808"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Donghan Bian","raw_affiliation_strings":["Centre Jean-Mabillon , \u00c9cole nationale des chartes -PSL , Paris , France","EPITA Research Laboratory , EPITA , Paris , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre Jean-Mabillon , \u00c9cole nationale des chartes -PSL , Paris , France","institution_ids":["https://openalex.org/I4210100316"]},{"raw_affiliation_string":"EPITA Research Laboratory , EPITA , Paris , France","institution_ids":["https://openalex.org/I4210138808"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130402470","display_name":"Marie Puren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100316","display_name":"\u00c9cole Nationale des Chartes","ror":"https://ror.org/013xvg556","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580","https://openalex.org/I4210100316"]},{"id":"https://openalex.org/I4210138808","display_name":"\u00c9cole Pour l'Informatique et les Techniques Avanc\u00e9es","ror":"https://ror.org/04r5ddq29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210138808"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marie Puren","raw_affiliation_strings":["Centre Jean-Mabillon , \u00c9cole nationale des chartes -PSL , Paris , France","EPITA Research Laboratory , EPITA , Paris , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre Jean-Mabillon , \u00c9cole nationale des chartes -PSL , Paris , France","institution_ids":["https://openalex.org/I4210100316"]},{"raw_affiliation_string":"EPITA Research Laboratory , EPITA , Paris , France","institution_ids":["https://openalex.org/I4210138808"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130402698","display_name":"Florian Cafiero","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100316","display_name":"\u00c9cole Nationale des Chartes","ror":"https://ror.org/013xvg556","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580","https://openalex.org/I4210100316"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Florian Cafiero","raw_affiliation_strings":["Centre Jean-Mabillon , \u00c9cole nationale des chartes -PSL , Paris , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre Jean-Mabillon , \u00c9cole nationale des chartes -PSL , Paris , France","institution_ids":["https://openalex.org/I4210100316"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24286341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.4230000078678131,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.4230000078678131,"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":0.09740000218153,"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/T10799","display_name":"Data Visualization and Analytics","score":0.04280000180006027,"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/feature","display_name":"Feature (linguistics)","score":0.30239999294281006},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2912999987602234},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2831999957561493},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2567000091075897},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.24779999256134033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6449999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49480000138282776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3880000114440918},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.24779999256134033},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2442999929189682},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.23090000450611115}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.latechclfl-1.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.23","pdf_url":"https://aclanthology.org/2026.latechclfl-1.23.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.latechclfl-1.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.23","pdf_url":"https://aclanthology.org/2026.latechclfl-1.23.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140105006.pdf","grobid_xml":"https://content.openalex.org/works/W7140105006.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph-based":[0],"Retrieval-Augmented":[1],"Generation":[2],"(RAG)":[3],"is":[4,24],"increasingly":[5],"used":[6],"to":[7,30,49,68,107,129,142],"explore":[8],"long,":[9],"heterogeneous,":[10],"and":[11,28,35,53,70,85,133],"weakly":[12],"structured":[13],"corpora,":[14],"including":[15],"historical":[16,59,73,131],"archives.However,":[17],"in":[18],"such":[19],"settings,":[20],"naive":[21],"full-corpus":[22,108],"indexing":[23],"often":[25],"computationally":[26],"costly":[27],"sensitive":[29],"OCR":[31],"noise,":[32],"document":[33],"redundancy,":[34],"topical":[36],"dispersion.In":[37],"this":[38,118],"paper,":[39],"we":[40],"investigate":[41],"corpus":[42],"pre-targeting":[43,65,92],"strategies":[44,93],"as":[45],"an":[46],"intermediate":[47],"layer":[48],"improve":[50,95],"the":[51,121,143],"efficiency":[52],"effectiveness":[54],"of":[55,64,72,113,123,146],"graph-based":[56,139],"RAG":[57,128,140],"for":[58,126,137],"research.We":[60],"evaluate":[61],"a":[62,77],"set":[63],"heuristics":[66],"tailored":[67],"single-hop":[69],"multi-hop":[71],"questions":[74],"on":[75],"HistoriQA-ThirdRepublic,":[76],"French":[78],"question-answering":[79],"dataset":[80],"derived":[81],"from":[82],"parliamentary":[83],"debates":[84],"contemporary":[86],"newspapers.Our":[87],"results":[88],"show":[89],"that":[90],"appropriate":[91],"can":[94],"retrieval":[96],"recall":[97],"by":[98,104],"3-5%":[99],"while":[100],"reducing":[101],"token":[102],"consumption":[103],"32-37%":[105],"compared":[106],"indexing,":[109],"without":[110],"degrading":[111],"coverage":[112],"relevant":[114],"documents.Beyond":[115],"performance":[116],"gains,":[117],"work":[119],"highlights":[120],"importance":[122],"corpus-level":[124],"optimization":[125],"applying":[127],"large-scale":[130],"collections,":[132],"provides":[134],"practical":[135],"insights":[136],"adapting":[138],"pipelines":[141],"specific":[144],"constraints":[145],"digitized":[147],"archives.":[148]},"counts_by_year":[],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2026-03-24T00:00:00"}