{"id":"https://openalex.org/W4384890923","doi":"https://doi.org/10.1145/3539618.3591885","title":"The JOKER Corpus: English-French Parallel Data for Multilingual Wordplay Recognition","display_name":"The JOKER Corpus: English-French Parallel Data for Multilingual Wordplay Recognition","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384890923","doi":"https://doi.org/10.1145/3539618.3591885"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3591885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3591885","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/10.1145/3539618.3591885","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023115127","display_name":"Liana Ermakova","orcid":"https://orcid.org/0000-0002-7598-7474"},"institutions":[{"id":"https://openalex.org/I161929037","display_name":"Universit\u00e9 de Bretagne Occidentale","ror":"https://ror.org/01b8h3982","country_code":"FR","type":"education","lineage":["https://openalex.org/I161929037"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Liana Ermakova","raw_affiliation_strings":["Universit\u00e9 de Bretagne Occidentale, Brest, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Bretagne Occidentale, Brest, France","institution_ids":["https://openalex.org/I161929037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113080254","display_name":"Anne-Gwenn Bosser","orcid":"https://orcid.org/0000-0002-0442-2660"},"institutions":[{"id":"https://openalex.org/I161929037","display_name":"Universit\u00e9 de Bretagne Occidentale","ror":"https://ror.org/01b8h3982","country_code":"FR","type":"education","lineage":["https://openalex.org/I161929037"]},{"id":"https://openalex.org/I180375564","display_name":"\u00c9cole nationale d'ing\u00e9nieurs de Brest","ror":"https://ror.org/02ypw0a72","country_code":"FR","type":"education","lineage":["https://openalex.org/I180375564"]},{"id":"https://openalex.org/I4210123702","display_name":"Laboratoire des Sciences et Techniques de l\u2019Information de la Communication et de la Connaissance","ror":"https://ror.org/0266kfd37","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I180375564","https://openalex.org/I201181511","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I4210123702","https://openalex.org/I4210127572","https://openalex.org/I4210145102","https://openalex.org/I4210148559","https://openalex.org/I4210159245","https://openalex.org/I4405260085"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Anne-Gwenn Bosser","raw_affiliation_strings":["\u00c9cole Nationale d'Ing\u00e9nieurs de Brest, Plouzan\u00e9, France","Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Technopole Brest Iroise CS 83818 29238 BREST cedex 3 - France)","Lab-STICC_COMMEDIA - Equipe COgnition, Models and Machines for Engaging Digital Interactive Applications (France)"],"affiliations":[{"raw_affiliation_string":"\u00c9cole Nationale d'Ing\u00e9nieurs de Brest, Plouzan\u00e9, France","institution_ids":["https://openalex.org/I180375564"]},{"raw_affiliation_string":"Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Technopole Brest Iroise CS 83818 29238 BREST cedex 3 - France)","institution_ids":["https://openalex.org/I161929037","https://openalex.org/I4210123702"]},{"raw_affiliation_string":"Lab-STICC_COMMEDIA - Equipe COgnition, Models and Machines for Engaging Digital Interactive Applications (France)","institution_ids":["https://openalex.org/I161929037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079733597","display_name":"Adam Jatowt","orcid":"https://orcid.org/0000-0001-7235-0665"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["AT","JP"],"is_corresponding":false,"raw_author_name":"Adam Jatowt","raw_affiliation_strings":["University of Innsbruck, Innsbruck, Austria","Kyoto University (Yoshidahonmachi, Sakyo Ward, Kyoto, Kyoto Prefecture 606-8501 - Japan)"],"affiliations":[{"raw_affiliation_string":"University of Innsbruck, Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]},{"raw_affiliation_string":"Kyoto University (Yoshidahonmachi, Sakyo Ward, Kyoto, Kyoto Prefecture 606-8501 - Japan)","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085860502","display_name":"Tristan Miller","orcid":"https://orcid.org/0000-0002-0749-1100"},"institutions":[{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Tristan Miller","raw_affiliation_strings":["Austrian Research Institute for Artificial Intelligence, Vienna, Austria","OFAI - Austrian Research Institute for Artificial Intelligence (Freyung 6/6, A-1010 Vienna Austria - Austria)"],"affiliations":[{"raw_affiliation_string":"Austrian Research Institute for Artificial Intelligence, Vienna, Austria","institution_ids":["https://openalex.org/I161878677"]},{"raw_affiliation_string":"OFAI - Austrian Research Institute for Artificial Intelligence (Freyung 6/6, A-1010 Vienna Austria - Austria)","institution_ids":["https://openalex.org/I161878677"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023115127"],"corresponding_institution_ids":["https://openalex.org/I161929037"],"apc_list":null,"apc_paid":null,"fwci":1.8874,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88437763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2796","last_page":"2806"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9994000196456909,"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":0.9945999979972839,"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/computer-science","display_name":"Computer science","score":0.799734354019165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6873174905776978},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6647273302078247},{"id":"https://openalex.org/keywords/clef","display_name":"Clef","score":0.5877739787101746},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4710048735141754},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41358840465545654},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4053404927253723},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.396999716758728},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.20281901955604553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.799734354019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6873174905776978},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6647273302078247},{"id":"https://openalex.org/C107763842","wikidata":"https://www.wikidata.org/wiki/Q181040","display_name":"Clef","level":3,"score":0.5877739787101746},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4710048735141754},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41358840465545654},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4053404927253723},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.396999716758728},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.20281901955604553},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3539618.3591885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3591885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3591885","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04299292v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04299292","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2023, Taipei Taiwan, France. pp.2796-2806, ⟨10.1145/3539618.3591885⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.1145/3539618.3591885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3591885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3591885","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7368347439","display_name":null,"funder_award_id":"ANR-19-GURE-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8318455765","display_name":null,"funder_award_id":"ANR-19","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384890923.pdf","grobid_xml":"https://content.openalex.org/works/W4384890923.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W19282688","https://openalex.org/W1538542877","https://openalex.org/W2014728052","https://openalex.org/W2084632905","https://openalex.org/W2090915937","https://openalex.org/W2093773668","https://openalex.org/W2101105183","https://openalex.org/W2122188028","https://openalex.org/W2124761544","https://openalex.org/W2251785914","https://openalex.org/W2278787942","https://openalex.org/W2549497593","https://openalex.org/W2616647696","https://openalex.org/W2620949368","https://openalex.org/W2751923720","https://openalex.org/W2753059774","https://openalex.org/W2791760305","https://openalex.org/W2798778974","https://openalex.org/W2894118680","https://openalex.org/W2945373472","https://openalex.org/W2947509090","https://openalex.org/W2951804840","https://openalex.org/W2952005787","https://openalex.org/W2963626623","https://openalex.org/W2966559663","https://openalex.org/W2970252517","https://openalex.org/W2981852735","https://openalex.org/W2995903708","https://openalex.org/W2997591727","https://openalex.org/W3006587931","https://openalex.org/W3034533484","https://openalex.org/W3046368065","https://openalex.org/W3093871477","https://openalex.org/W3116985850","https://openalex.org/W3144680086","https://openalex.org/W3183822815","https://openalex.org/W3184074368","https://openalex.org/W4223652727","https://openalex.org/W4234143269","https://openalex.org/W4288089799","https://openalex.org/W4289766921","https://openalex.org/W4292939182","https://openalex.org/W4327498004"],"related_works":["https://openalex.org/W1839123017","https://openalex.org/W4232115401","https://openalex.org/W1592594506","https://openalex.org/W2970828463","https://openalex.org/W3138512925","https://openalex.org/W117735687","https://openalex.org/W2917705549","https://openalex.org/W2184096423","https://openalex.org/W2611815462","https://openalex.org/W2397564744"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advances":[2],"in":[3,37,87,114,172],"information":[4,187],"retrieval":[5,63,89],"and":[6,45,64,67,78,85,90,106,135,167],"natural":[7],"language":[8,43],"processing,":[9],"rhetorical":[10],"devices":[11],"that":[12,157],"exploit":[13],"ambiguity":[14],"or":[15,175],"subvert":[16],"linguistic":[17],"rules":[18],"remain":[19],"a":[20,32,80,182],"challenge":[21],"for":[22,53,60,69,83,95,132],"such":[23],"systems.":[24],"However,":[25],"corpus-based":[26],"analysis":[27],"of":[28,35,92,121,125,141,148],"wordplay":[29,111,164],"has":[30],"been":[31],"perennial":[33],"topic":[34],"scholarship":[36],"the":[38,58,88,96,133,149],"humanities,":[39],"including":[40],"literary":[41],"criticism,":[42],"education,":[44],"translation":[46],"studies.":[47],"The":[48],"immense":[49],"data-gathering":[50],"effort":[51],"required":[52],"these":[54],"studies":[55],"points":[56],"to":[57,161],"need":[59],"specialized":[61],"text":[62],"classification":[65],"technology,":[66],"consequently":[68],"appropriate":[70],"test":[71,178],"collections.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76,118,128,137],"introduce":[77,119],"analyze":[79],"new":[81],"dataset":[82],"research":[84],"applications":[86],"processing":[91],"wordplay.":[93],"Developed":[94],"JOKER":[97],"track":[98],"at":[99],"CLEF":[100],"2023,":[101],"our":[102],"annotated":[103],"corpus":[104],"extends":[105],"improves":[107],"upon":[108],"past":[109],"English":[110],"detection":[112],"datasets":[113],"several":[115],"ways.":[116],"First,":[117],"hundreds":[120],"additional":[122],"positive":[123,150],"examples":[124,140],"wordplay;":[126],"second,":[127],"provide":[129,138],"French":[130],"translations":[131],"examples;":[134],"third,":[136],"negative":[139],"non-wordplay":[142],"with":[143],"characteristics":[144],"closely":[145],"matching":[146],"those":[147],"examples.":[151],"This":[152],"last":[153],"feature":[154],"helps":[155],"ensure":[156],"AI":[158],"models":[159],"learn":[160],"effectively":[162],"distinguish":[163],"from":[165],"non-wordplay,":[166],"not":[168],"simply":[169],"texts":[170],"differing":[171],"length,":[173],"style,":[174],"vocabulary.":[176],"Our":[177],"collection":[179],"represents":[180],"then":[181],"step":[183],"towards":[184],"wordplay-aware":[185],"multilingual":[186],"retrieval.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}