{"id":"https://openalex.org/W4411120543","doi":"https://doi.org/10.18653/v1/2025.mwe-1.8","title":"MultiCoPIE: A Multilingual Corpus of Potentially Idiomatic Expressions for Cross-lingual PIE Disambiguation","display_name":"MultiCoPIE: A Multilingual Corpus of Potentially Idiomatic Expressions for Cross-lingual PIE Disambiguation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411120543","doi":"https://doi.org/10.18653/v1/2025.mwe-1.8"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.mwe-1.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.mwe-1.8","pdf_url":"https://aclanthology.org/2025.mwe-1.8.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 21st Workshop on Multiword Expressions (MWE 2025)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.mwe-1.8.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093293903","display_name":"Uliana Sentsova","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Uliana Sentsova","raw_affiliation_strings":["Saarland University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saarland University ,","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117865315","display_name":"Debora Ciminari","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Debora Ciminari","raw_affiliation_strings":["University of Bologna ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bologna ,","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049194403","display_name":"Josef van Genabith","orcid":"https://orcid.org/0000-0003-1322-7944"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Josef Van Genabith","raw_affiliation_strings":["DFKI GmbH , Saarland Informatics Campus ,","Saarland University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI GmbH , Saarland Informatics Campus ,","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I91712215"]},{"raw_affiliation_string":"Saarland University ,","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029540488","display_name":"Cristina Espa\u00f1a-Bonet","orcid":"https://orcid.org/0000-0001-5414-4710"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]},{"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":["DE","ES"],"is_corresponding":false,"raw_author_name":"Cristina Espa\u00f1a-Bonet","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC-CNS)","DFKI GmbH , Saarland Informatics Campus ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC-CNS)","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"raw_affiliation_string":"DFKI GmbH , Saarland Informatics Campus ,","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"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":0.08111897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},{"id":"https://openalex.org/T12881","display_name":"linguistics and terminology studies","score":0.9474999904632568,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7731571197509766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7680806517601013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6219605207443237},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4816093146800995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731571197509766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7680806517601013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6219605207443237},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4816093146800995},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.mwe-1.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.mwe-1.8","pdf_url":"https://aclanthology.org/2025.mwe-1.8.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 21st Workshop on Multiword Expressions (MWE 2025)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.mwe-1.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.mwe-1.8","pdf_url":"https://aclanthology.org/2025.mwe-1.8.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 21st Workshop on Multiword Expressions (MWE 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G1951765764","display_name":null,"funder_award_id":"SFB 1102","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411120543.pdf","grobid_xml":"https://content.openalex.org/works/W4411120543.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Language":[0],"models":[1],"are":[2],"able":[3],"to":[4,8,86,102,114,119],"handle":[5],"compositionality":[6],"and,":[7],"some":[9],"extent,":[10],"noncompositional":[11],"phenomena":[12],"such":[13,57],"as":[14,58,66,68],"semantic":[15,60],"idiosyncrasy,":[16],"a":[17],"feature":[18],"most":[19],"prominent":[20],"in":[21,36,73,96,106,159],"the":[22,28,42,103,107,111,126,132,135,145,171,176],"case":[23],"of":[24,45,55,63,92,128,134,173,185],"idioms.This":[25],"work":[26],"introduces":[27],"MultiCoPIE":[29,108,146],"corpus":[30,47,50],"that":[31,155],"includes":[32],"potentially":[33,93],"idiomatic":[34,71,94,140],"expressions":[35,72,95,141,154],"Catalan,":[37],"Italian,":[38],"and":[39,89,142,164],"Russian,":[40],"extending":[41],"language":[43],"coverage":[44],"PIE":[46],"data.The":[48],"new":[49,76],"provides":[51],"additional":[52],"linguistic":[53],"features":[54],"idioms,":[56],"their":[59,69],"compositionality,":[61],"part-of-speech":[62],"idiom":[64],"head":[65],"well":[67],"corresponding":[70],"English.With":[74],"this":[75,166],"resource":[77],"at":[78],"hand,":[79],"we":[80],"first":[81],"fine-tune":[82],"an":[83,116],"XLM-RoBERTa":[84],"model":[85],"classify":[87],"figurative":[88],"literal":[90],"usage":[91],"English.We":[97],"then":[98],"study":[99],"cross-lingual":[100,174,187],"transfer":[101],"languages":[104,120],"represented":[105],"corpus,":[109],"evaluating":[110],"model's":[112],"ability":[113],"generalize":[115],"idiom-related":[117],"task":[118],"not":[121],"seen":[122],"during":[123],"fine-tuning.We":[124],"show":[125],"effect":[127],"'cross-lingual":[129],"lexical":[130],"overlap':":[131],"performance":[133],"model,":[136],"fine-tuned":[137],"on":[138,144,180],"English":[139,160],"tested":[143],"languages,":[147],"increases":[148],"significantly":[149],"when":[150,190],"classifying":[151],"'shared":[152],"idioms'idiomatic":[153],"have":[156],"direct":[157],"counterparts":[158],"with":[161],"similar":[162,194],"form":[163],"meaning.While":[165],"observation":[167],"raises":[168],"questions":[169],"about":[170],"generalizability":[172],"learning,":[175],"results":[177],"from":[178],"experiments":[179],"PIEs":[181],"demonstrate":[182],"strong":[183],"evidence":[184],"effective":[186],"transfer,":[188],"even":[189],"accounting":[191],"for":[192],"idioms":[193],"across":[195],"languages.":[196]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
