{"id":"https://openalex.org/W7126033397","doi":"https://doi.org/10.5281/zenodo.18411374","title":"Onthology guided RAG augmentation - evaluation framework for experimentation with different augmentation strategies , extration of corpus and evaluation","display_name":"Onthology guided RAG augmentation - evaluation framework for experimentation with different augmentation strategies , extration of corpus and evaluation","publication_year":2026,"publication_date":"2026-01-29","ids":{"openalex":"https://openalex.org/W7126033397","doi":"https://doi.org/10.5281/zenodo.18411374"},"language":null,"primary_location":{"id":"pmh:doi:10.5281/zenodo.18411373","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"raw_type":"Software"},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124184432","display_name":"Marc Alier","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alier, Marc","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya"],"raw_orcid":"https://orcid.org/0000-0003-3922-1516","affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088586722","display_name":"Mar\u00eda Jos\u00e9 Casany","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Casany, Mar\u00eda Jos\u00e9","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya"],"raw_orcid":"https://orcid.org/0000-0002-5072-6745","affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124166647","display_name":"Juanan Pererira","orcid":null},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pererira, Juanan","raw_affiliation_strings":["University of the Basque Country"],"raw_orcid":"https://orcid.org/0000-0002-7935-3612","affiliations":[{"raw_affiliation_string":"University of the Basque Country","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124284272","display_name":"Francisco Jos\u00e9 GARC\u00cdA-PE\u00d1ALVO","orcid":null},"institutions":[{"id":"https://openalex.org/I184999862","display_name":"Universidad de Salamanca","ror":"https://ror.org/02f40zc51","country_code":"ES","type":"education","lineage":["https://openalex.org/I184999862"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"GARC\u00cdA-PE\u00d1ALVO, Francisco Jos\u00e9","raw_affiliation_strings":["Universidad de Salamanca"],"raw_orcid":"https://orcid.org/0000-0001-9987-5584","affiliations":[{"raw_affiliation_string":"Universidad de Salamanca","institution_ids":["https://openalex.org/I184999862"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/acronym","display_name":"Acronym","score":0.8190000057220459},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5878999829292297},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5874000191688538},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5728999972343445},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5530999898910522},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5110999941825867},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41499999165534973},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4004000127315521}],"concepts":[{"id":"https://openalex.org/C482391","wikidata":"https://www.wikidata.org/wiki/Q101244","display_name":"Acronym","level":2,"score":0.8190000057220459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771000266075134},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5878999829292297},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5874000191688538},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5728999972343445},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45559999346733093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42989999055862427},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3865000009536743},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.5281/zenodo.18411373","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"raw_type":"Software"},{"id":"doi:10.5281/zenodo.18411374","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18411374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.5281/zenodo.18411373","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"raw_type":"Software"},"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":{"This":[0,39],"repository":[1,40],"contains":[2],"the":[3],"implementation":[4],"code,":[5],"ontology":[6],"builder,":[7],"and":[8,37,53,64],"evaluation":[9],"scripts":[10],"for":[11,73,86,104],"our":[12],"paper":[13],"on":[14,70,97],"improving":[15],"Retrieval-Augmented":[16],"Generation":[17],"(RAG)":[18],"systems":[19,27],"in":[20,84],"acronym-heavy":[21],"educational":[22],"environments.":[23],"Overview":[24],"Educational":[25],"RAG":[26],"struggle":[28],"with":[29],"acronyms":[30],"due":[31],"to":[32,81],"vocabulary":[33],"mismatch":[34],"between":[35],"queries":[36,88],"documents.":[38],"implements":[41],"a":[42],"scalable":[43],"solution":[44],"that:":[45],"Builds":[46],"corpus-scale":[47],"acronym":[48,87],"ontologies":[49],"through":[50],"multi-phase":[51],"extraction":[52],"disambiguation":[54],"Augments":[55],"retrieval":[56],"at":[57],"two":[58],"leverage":[59],"points:":[60],"Query-Time":[61],"Augmentation":[62],"(QTA)":[63],"Ingestion-Time":[65],"Enrichment":[66],"(ITE)":[67],"Fine-tunes":[68],"embedders":[69,106],"acronym\u2194expansion":[71],"pairs":[72],"improved":[74],"semantic":[75],"matching":[76],"Achieves":[77],"substantial":[78],"gains:":[79],"Up":[80],"102%":[82],"improvement":[83,103],"Recall@10":[85,96],"Key":[89],"Results":[90],"QTA":[91],"alone:":[92],"+55.3%":[93],"nDCG@10,":[94],"+67.2%":[95],"average":[98],"QTA+ITE":[99],"combined:":[100],"+64.5%":[101],"overall":[102],"open-source":[105],"Small":[107],"augmented":[108],"models":[109,115],"match":[110],"or":[111],"exceed":[112],"larger":[113],"proprietary":[114],"while":[116],"eliminating":[117],"API":[118],"costs":[119]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-30T00:00:00"}
