{"id":"https://openalex.org/W4411120096","doi":"https://doi.org/10.18653/v1/2025.mwe-1.7","title":"A European Portuguese corpus annotated for verbal idioms","display_name":"A European Portuguese corpus annotated for verbal idioms","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411120096","doi":"https://doi.org/10.18653/v1/2025.mwe-1.7"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.mwe-1.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.mwe-1.7","pdf_url":"https://aclanthology.org/2025.mwe-1.7.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-1.7.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103242320","display_name":"David Antunes","orcid":"https://orcid.org/0000-0003-1444-2881"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"David Antunes","raw_affiliation_strings":["INESC ID Lisboa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INESC ID Lisboa","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059492029","display_name":"Jorge Baptista","orcid":"https://orcid.org/0000-0003-4603-4364"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jorge Baptista","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061593183","display_name":"Nuno Mamede","orcid":"https://orcid.org/0000-0001-6033-158X"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno J. Mamede","raw_affiliation_strings":["INESC ID Lisboa IST , Univ. Lisboa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INESC ID Lisboa IST , Univ. Lisboa","institution_ids":["https://openalex.org/I121345201"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.08222916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"58","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.968999981880188,"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":0.968999981880188,"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/T13260","display_name":"Linguistics and Language Studies","score":0.9456999897956848,"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"}},{"id":"https://openalex.org/T12341","display_name":"Spanish Linguistics and Language Studies","score":0.9430999755859375,"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/portuguese","display_name":"Portuguese","score":0.7561770677566528},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6535646915435791},{"id":"https://openalex.org/keywords/european-portuguese","display_name":"European Portuguese","score":0.5909458994865417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5816676616668701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4466606378555298},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4144537150859833},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05181702971458435}],"concepts":[{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.7561770677566528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6535646915435791},{"id":"https://openalex.org/C2780939345","wikidata":"https://www.wikidata.org/wiki/Q922399","display_name":"European Portuguese","level":3,"score":0.5909458994865417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5816676616668701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4466606378555298},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4144537150859833},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05181702971458435}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.mwe-1.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.mwe-1.7","pdf_url":"https://aclanthology.org/2025.mwe-1.7.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-1.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.mwe-1.7","pdf_url":"https://aclanthology.org/2025.mwe-1.7.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":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1340648235","display_name":null,"funder_award_id":"HORIZON-CL2-2022-TRANSFORMATIONS-01","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G1740015287","display_name":null,"funder_award_id":"10.54499/UIDB/50021/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G2441341484","display_name":"Instituto de Engenharia de Sistemas e Computadores, Investiga\u00e7\u00e3o e Desenvolvimento em Lisboa","funder_award_id":"UIDB/50021/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3019180854","display_name":null,"funder_award_id":"DOI: 10.54499/UIDB/50021/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G5885653337","display_name":"Intelligent Reading Improvement System for Fundamental and Transversal Skills Development","funder_award_id":"101094837","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6997658380","display_name":null,"funder_award_id":"10.54499","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411120096.pdf","grobid_xml":"https://content.openalex.org/works/W4411120096.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W1591253349","https://openalex.org/W2759367949"],"related_works":["https://openalex.org/W1911260","https://openalex.org/W2479207534","https://openalex.org/W4377968335","https://openalex.org/W3204019825","https://openalex.org/W3083760992","https://openalex.org/W616758433","https://openalex.org/W2490883683","https://openalex.org/W4229756535","https://openalex.org/W2182374716","https://openalex.org/W2160083603"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,23,32,47,57,68,80,117,125],"construction":[4],"of":[5,34,37,59,62,82,85,88,116,124],"VIDiom-PT,":[6],"a":[7,19,71,83],"corpus":[8,127],"in":[9,41,46,65,79,93,98],"European":[10,99],"Portuguese":[11],"annotated":[12,120,126],"for":[13,56,74,110],"verbal":[14,63,91],"idioms":[15,64,92],"(e.g.'O":[16],"Rui":[17],"bateu":[18],"bota'":[20],"(lit.\"Rui":[21],"hit":[22],"boot\")":[24],"\"Rui":[25],"died\").This":[26],"linguistic":[27],"resource":[28],"aims":[29],"to":[30],"support":[31],"development":[33],"systems":[35],"capable":[36],"processing":[38],"such":[39],"constructions":[40],"this":[42],"language":[43],"variety.To":[44],"assist":[45],"annotation":[48,81],"effort,":[49],"two":[50],"tools":[51],"were":[52],"built.The":[53],"first":[54],"allows":[55],"detection":[58],"possible":[60],"instances":[61,87],"texts,":[66],"while":[67],"second":[69],"provides":[70],"graphical":[72],"interface":[73],"annotating":[75],"them.This":[76],"effort":[77],"culminated":[78],"total":[84],"5,178":[86],"747":[89],"different":[90],"more":[94],"than":[95],"200,000":[96],"sentences":[97],"Portuguese.A":[100],"highly":[101],"reliable":[102],"inter-annotator":[103],"agreement":[104],"was":[105],"achieved,":[106],"using":[107],"Krippendorff's":[108],"alpha":[109],"nominal":[111],"data":[112,118],"(0.869)":[113],"with":[114],"5%":[115],"independently":[119],"by":[121],"3":[122],"experts.Part":[123],"is":[128],"also":[129],"made":[130],"publicly":[131],"available.":[132]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
