{"id":"https://openalex.org/W4412888068","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1042","title":"KE-MHISTO: Towards a Multilingual Historical Knowledge Extraction Benchmark for Addressing the Long-Tail Problem","display_name":"KE-MHISTO: Towards a Multilingual Historical Knowledge Extraction Benchmark for Addressing the Long-Tail Problem","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888068","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1042"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1042","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1042","pdf_url":"https://aclanthology.org/2025.findings-acl.1042.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1042.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041804036","display_name":"Arianna Graciotti","orcid":"https://orcid.org/0009-0004-7918-809X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arianna Graciotti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048737002","display_name":"Leonardo Piano","orcid":"https://orcid.org/0000-0003-1047-5491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leonardo Piano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048936818","display_name":"Nicolas Lazzari","orcid":"https://orcid.org/0000-0002-1601-7689"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Lazzari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014143084","display_name":"Enrico Daga","orcid":"https://orcid.org/0000-0002-3184-5407"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Enrico Daga","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013191092","display_name":"Rocco Tripodi","orcid":"https://orcid.org/0000-0003-2483-8564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rocco Tripodi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007281490","display_name":"Valentina Presutti","orcid":"https://orcid.org/0000-0002-9380-5160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Valentina Presutti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019584956","display_name":"Livio Pompianu","orcid":"https://orcid.org/0000-0003-3745-4324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Livio Pompianu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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":0.20176125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20316","last_page":"20339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.4487999975681305,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.4487999975681305,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7928374409675598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6732325553894043},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5494189262390137},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.41485902667045593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40674370527267456},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38923680782318115},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35637927055358887},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10470426082611084},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06353643536567688},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05743822455406189}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7928374409675598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6732325553894043},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5494189262390137},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.41485902667045593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40674370527267456},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38923680782318115},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35637927055358887},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10470426082611084},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06353643536567688},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05743822455406189},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1042","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1042","pdf_url":"https://aclanthology.org/2025.findings-acl.1042.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arpi.unipi.it:11568/1343751","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1343751","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:iris.unica.it:11584/457806","is_oa":true,"landing_page_url":"https://hdl.handle.net/11584/457806","pdf_url":null,"source":{"id":"https://openalex.org/S4377196293","display_name":"UNICA IRIS Institutional Research Information System (University of Cagliari)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172446870","host_organization_name":"University of Cagliari","host_organization_lineage":["https://openalex.org/I172446870"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1042","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1042","pdf_url":"https://aclanthology.org/2025.findings-acl.1042.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3216080345","display_name":null,"funder_award_id":"101004746","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4508289328","display_name":null,"funder_award_id":"PE00000013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888068.pdf","grobid_xml":"https://content.openalex.org/works/W4412888068.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W93075631","https://openalex.org/W3005434123","https://openalex.org/W2599205313","https://openalex.org/W2076251662","https://openalex.org/W4231842067"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"face":[4],"significant":[5],"challenges":[6,107],"when":[7,54],"queried":[8],"about":[9],"long-tail":[10,133],"knowledge,":[11,83],"i.e.,":[12],"information":[13],"that":[14,91,113],"is":[15],"rarely":[16],"encountered":[17],"during":[18],"their":[19,41],"training":[20],"process.These":[21],"difficulties":[22],"arise":[23],"due":[24],"to":[25,37,49,61,101,121],"the":[26,35,78,126],"inherent":[27],"sparsity":[28],"of":[29,80,97,128],"such":[30],"data.Furthermore,":[31],"LLMs":[32],"often":[33],"lack":[34],"ability":[36],"verify":[38],"or":[39],"ground":[40],"responses":[42],"in":[43,77,85],"authoritative":[44],"sources,":[45],"which":[46],"can":[47,117],"lead":[48],"plausible":[50],"yet":[51],"inaccurate":[52],"outputs":[53],"addressing":[55],"infrequent":[56],"subject":[57],"matter.Our":[58],"work":[59],"aims":[60],"investigate":[62],"these":[63],"phenomena":[64],"by":[65],"introducing":[66],"KE-MHISTO,":[67],"a":[68],"multilingual":[69,115],"benchmark":[70],"for":[71,108,132],"Entity":[72],"Linking":[73],"and":[74,88],"Question":[75],"Answering":[76],"domain":[79],"historical":[81],"music":[82],"available":[84],"both":[86],"Italian":[87],"English.We":[89],"demonstrate":[90],"KE-MHISTO":[92],"provides":[93],"significantly":[94,122],"broader":[95],"coverage":[96],"longtail":[98],"knowledge":[99,134],"compared":[100],"existing":[102],"alternatives.Moreover,":[103],"it":[104],"poses":[105],"substantial":[106],"state-of-the-art":[109],"models.Our":[110],"experiments":[111],"reveal":[112],"smaller,":[114],"models":[116],"achieve":[118],"performance":[119],"comparable":[120],"larger":[123],"counterparts,":[124],"highlighting":[125],"potential":[127],"efficient,":[129],"language-aware":[130],"approaches":[131],"extraction.":[135]},"counts_by_year":[],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}