{"id":"https://openalex.org/W4390946519","doi":"https://doi.org/10.1145/3494572","title":"What Is in a &lt;unittitle&gt;? Cross-lingual Topic Detection &amp; Information Retrieval in Archives Portal Europe","display_name":"What Is in a &lt;unittitle&gt;? Cross-lingual Topic Detection &amp; Information Retrieval in Archives Portal Europe","publication_year":2024,"publication_date":"2024-01-17","ids":{"openalex":"https://openalex.org/W4390946519","doi":"https://doi.org/10.1145/3494572"},"language":"en","primary_location":{"id":"doi:10.1145/3494572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3494572","pdf_url":null,"source":{"id":"https://openalex.org/S4210184050","display_name":"Journal on Computing and Cultural Heritage","issn_l":"1556-4711","issn":["1556-4711","1556-4673"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Computing and Cultural Heritage","raw_type":"journal-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/A5002171696","display_name":"Marta Musso","orcid":"https://orcid.org/0000-0002-3728-3548"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marta Musso","raw_affiliation_strings":["King's College London, London, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London, London, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028562430","display_name":"Kerstin Arnold","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152121","display_name":"Internet Memory Foundation","ror":"https://ror.org/04pys4598","country_code":"NL","type":"nonprofit","lineage":["https://openalex.org/I4210152121"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kerstin Arnold","raw_affiliation_strings":["Archives Portal Europe Foundation, The Hague, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Archives Portal Europe Foundation, The Hague, Netherlands","institution_ids":["https://openalex.org/I4210152121"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064977687","display_name":"Federico Nanni","orcid":"https://orcid.org/0000-0003-2484-4331"},"institutions":[{"id":"https://openalex.org/I125680101","display_name":"Turing Institute","ror":"https://ror.org/02x2mw849","country_code":"GB","type":"facility","lineage":["https://openalex.org/I125680101"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Federico Nanni","raw_affiliation_strings":["TURING Institute London, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TURING Institute London, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I125680101"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019542400","display_name":"Beatrice Cannelli","orcid":"https://orcid.org/0000-0002-8645-9503"},"institutions":[{"id":"https://openalex.org/I2802488147","display_name":"School of Advanced Study","ror":"https://ror.org/039594g80","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I2802488147"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Beatrice Cannelli","raw_affiliation_strings":["School of Advanced Studies, London, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Advanced Studies, London, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I2802488147"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.729,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73702593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"17","issue":"2","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9979000091552734,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9951000213623047,"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/national-archives","display_name":"National archives","score":0.5501176714897156},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.5464138984680176},{"id":"https://openalex.org/keywords/archival-science","display_name":"Archival science","score":0.5454060435295105},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.48641514778137207},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.4682510793209076},{"id":"https://openalex.org/keywords/news-aggregator","display_name":"News aggregator","score":0.42497190833091736},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.4173702895641327},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4149106740951538},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41290047764778137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.33325251936912537},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.32077455520629883},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.10906481742858887}],"concepts":[{"id":"https://openalex.org/C2781300351","wikidata":"https://www.wikidata.org/wiki/Q2122214","display_name":"National archives","level":2,"score":0.5501176714897156},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.5464138984680176},{"id":"https://openalex.org/C520346617","wikidata":"https://www.wikidata.org/wiki/Q380313","display_name":"Archival science","level":2,"score":0.5454060435295105},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48641514778137207},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.4682510793209076},{"id":"https://openalex.org/C180505990","wikidata":"https://www.wikidata.org/wiki/Q498267","display_name":"News aggregator","level":2,"score":0.42497190833091736},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.4173702895641327},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4149106740951538},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41290047764778137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.33325251936912537},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.32077455520629883},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.10906481742858887},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3494572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3494572","pdf_url":null,"source":{"id":"https://openalex.org/S4210184050","display_name":"Journal on Computing and Cultural Heritage","issn_l":"1556-4711","issn":["1556-4711","1556-4673"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Computing and Cultural Heritage","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1484475658","https://openalex.org/W1540550673","https://openalex.org/W1560279844","https://openalex.org/W1832693441","https://openalex.org/W1880262756","https://openalex.org/W1884638619","https://openalex.org/W1978000310","https://openalex.org/W2002972549","https://openalex.org/W2063904635","https://openalex.org/W2065938813","https://openalex.org/W2068297964","https://openalex.org/W2085187375","https://openalex.org/W2144135958","https://openalex.org/W2256643272","https://openalex.org/W2326119785","https://openalex.org/W2342934368","https://openalex.org/W2487287669","https://openalex.org/W2495788958","https://openalex.org/W2597289420","https://openalex.org/W2604272474","https://openalex.org/W2741212913","https://openalex.org/W2755092149","https://openalex.org/W2783064254","https://openalex.org/W2799915114","https://openalex.org/W2937938457","https://openalex.org/W2972428363","https://openalex.org/W3022421070","https://openalex.org/W3037831233","https://openalex.org/W3128878409","https://openalex.org/W3138162398","https://openalex.org/W4206466396","https://openalex.org/W4242822767","https://openalex.org/W4245861846","https://openalex.org/W4293651439"],"related_works":["https://openalex.org/W2746392713","https://openalex.org/W4251369848","https://openalex.org/W2163748916","https://openalex.org/W2002966468","https://openalex.org/W3167700301","https://openalex.org/W2590656888","https://openalex.org/W3206437441","https://openalex.org/W2092940671","https://openalex.org/W4321100839","https://openalex.org/W2889536601"],"abstract_inverted_index":{"Archives":[0,69,126,170],"Portal":[1,70,127],"Europe":[2,71,128],"(APE,":[3],"www.archivesportaleurope.net":[4],")":[5],"is":[6,65,129,200,319],"the":[7,21,68,87,102,120,139,142,150,164,167,181,190,193,207,279,307,336,343],"portal":[8,151],"of":[9,27,47,76,90,105,110,119,145,160,166,195,204,209,234,287,328,335,338],"European":[10],"archives,":[11,53,55,59],"an":[12,73,201,288],"aggregator":[13],"that":[14,83,162,186],"connects":[15],"on":[16,321],"a":[17,45,157,239,246,265,296,314,326],"single":[18,91],"research":[19,112,121,215,241,252],"point":[20],"catalogues":[22],"and":[23,31,43,57,62,79,141,231,253,269,282,334,346],"digitised":[24],"archival":[25,48,81,88,103,111,146,205,214,221,226,251],"material":[26,37,89,147,312],"all":[28],"archives":[29,78,256],"in":[30,149,192,264,295,331],"about":[32],"Europe.":[33],"It":[34,64],"currently":[35,135],"hosts":[36],"from":[38,44,228],"more":[39],"than":[40],"30":[41],"countries":[42,230],"variety":[46],"institutions":[49,82,92,235],"(such":[50],"as":[51,304],"State":[52,77],"city":[54],"university":[56],"parish":[58],"private":[60],"institutions,":[61],"more).":[63],"maintained":[66,136],"by":[67,125,130,138,175],"Foundation,":[72],"international":[74],"consortium":[75],"other":[80],"aim":[84],"to":[85,97,101,155,249,254,257,260,309,341],"connect":[86],"into":[93,238],"one":[94],"digital":[95,211,220],"repository":[96],"allow":[98,255],"universal":[99],"access":[100],"heritage":[104],"Europe,":[106],"promoting":[107],"new":[108,217],"forms":[109],"beyond":[113],"national":[114,268],"or":[115,273],"local":[116],"boundaries.":[117],"One":[118],"tools":[122,218],"made":[123],"available":[124],"topics;":[131],"however,":[132],"these":[133],"are":[134,171,236,274],"manually":[137],"archivists,":[140],"vast":[143],"amount":[144],"ingested":[148],"makes":[152],"it":[153],"impossible":[154],"have":[156],"comprehensive":[158],"body":[159],"topics":[161],"describe":[163],"whole":[165],"APE":[168],"repository.":[169],"traditionally":[172],"not":[173],"organised":[174],"their":[176,196],"subject":[177],"content,":[178],"but":[179],"around":[180,313],"entity":[182],"(person,":[183],"organization,":[184],"body)":[185],"created":[187],"and/or":[188],"collected":[189],"documents":[191],"course":[194],"activities.":[197],"While":[198],"this":[199],"undisputed":[202],"pillar":[203],"management,":[206],"availability":[208],"online":[210],"repositories":[212],"for":[213,219,284,291,306],"requires":[216],"research,":[222],"particularly":[223],"when":[224],"different":[225,229,232,332],"traditions":[227],"types":[233],"merged":[237],"unique":[240],"portal.":[242],"Topic":[243],"detection":[244,294],"becomes":[245],"fundamental":[247],"tool":[248,290],"guide":[250],"be":[258],"accessible":[259],"potentially":[261],"world-wide":[262],"users":[263],"situation":[266],"where":[267,300],"linguistics":[270],"barriers":[271],"blur":[272],"re-defined.":[275],"This":[276],"article":[277],"presents":[278],"preliminary":[280],"results":[281],"plan":[283],"future":[285],"iterations":[286],"AI":[289],"automated":[292],"topic":[293],"multi-":[297],"lingual":[298],"environment,":[299],"human-created":[301],"taxonomies":[302],"act":[303],"bases":[305],"algorithms":[308],"aggregate":[310],"relevant":[311,344],"specific":[315],"topic.":[316],"The":[317],"development":[318],"based":[320],"supervised":[322],"machine":[323],"learning,":[324],"with":[325],"combination":[327],"human":[329],"inputs":[330],"languages,":[333],"usage":[337],"Wikipedia":[339],"pages":[340],"model":[342],"vocabulary":[345],"entities.":[347]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
