{"id":"https://openalex.org/W4401954369","doi":"https://doi.org/10.1007/s10579-024-09763-7","title":"PARSEME-AR: Arabic reference corpus for multiword expressions using PARSEME annotation guidelines","display_name":"PARSEME-AR: Arabic reference corpus for multiword expressions using PARSEME annotation guidelines","publication_year":2024,"publication_date":"2024-08-28","ids":{"openalex":"https://openalex.org/W4401954369","doi":"https://doi.org/10.1007/s10579-024-09763-7"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-024-09763-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-024-09763-7","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s10579-024-09763-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032089825","display_name":"Najet Hadj Mohamed","orcid":null},"institutions":[{"id":"https://openalex.org/I110017253","display_name":"Universit\u00e9 de Tours","ror":"https://ror.org/02wwzvj46","country_code":"FR","type":"education","lineage":["https://openalex.org/I110017253"]},{"id":"https://openalex.org/I4210136805","display_name":"Laboratoire d'Informatique Fondamentale et Appliqu\u00e9e de Tours","ror":"https://ror.org/03r938j26","country_code":"FR","type":"facility","lineage":["https://openalex.org/I110017253","https://openalex.org/I4210136805"]},{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]},{"id":"https://openalex.org/I4210119561","display_name":"Digital Research Centre of Sfax","ror":"https://ror.org/02s48dm85","country_code":"TN","type":"facility","lineage":["https://openalex.org/I4210119561"]}],"countries":["FR","TN"],"is_corresponding":true,"raw_author_name":"Najet Hadj Mohamed","raw_affiliation_strings":["LIFAT, ICVL, University of Tours, 37000, Tours, France","MIRACL, University of Sfax, 3029, Sfax, Tunisia","LIFAT - Laboratoire d'Informatique Fondamentale et Appliqu\u00e9e de Tours (64, Avenue Jean Portalis, 37200 Tours - France)","MIRACL - Multimedia, InfoRmation systems and Advanced Computing Laboratory (Route de Tunis, km 10, BP 242, Sakiet Ezziet, 3021 SFAX - Tunisia)"],"affiliations":[{"raw_affiliation_string":"LIFAT, ICVL, University of Tours, 37000, Tours, France","institution_ids":["https://openalex.org/I4210136805","https://openalex.org/I110017253"]},{"raw_affiliation_string":"MIRACL, University of Sfax, 3029, Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]},{"raw_affiliation_string":"LIFAT - Laboratoire d'Informatique Fondamentale et Appliqu\u00e9e de Tours (64, Avenue Jean Portalis, 37200 Tours - France)","institution_ids":["https://openalex.org/I4210136805"]},{"raw_affiliation_string":"MIRACL - Multimedia, InfoRmation systems and Advanced Computing Laboratory (Route de Tunis, km 10, BP 242, Sakiet Ezziet, 3021 SFAX - Tunisia)","institution_ids":["https://openalex.org/I4210119561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082292934","display_name":"Ch\u00e9rifa Ben Khelil","orcid":"https://orcid.org/0000-0001-7955-9736"},"institutions":[{"id":"https://openalex.org/I110017253","display_name":"Universit\u00e9 de Tours","ror":"https://ror.org/02wwzvj46","country_code":"FR","type":"education","lineage":["https://openalex.org/I110017253"]},{"id":"https://openalex.org/I4210136805","display_name":"Laboratoire d'Informatique Fondamentale et Appliqu\u00e9e de Tours","ror":"https://ror.org/03r938j26","country_code":"FR","type":"facility","lineage":["https://openalex.org/I110017253","https://openalex.org/I4210136805"]},{"id":"https://openalex.org/I117841876","display_name":"Universit\u00e9 Paris-Panth\u00e9on-Assas","ror":"https://ror.org/04qb2qm38","country_code":"FR","type":"education","lineage":["https://openalex.org/I117841876"]},{"id":"https://openalex.org/I2801479458","display_name":"Engineering School of Information and Digital Technologies","ror":"https://ror.org/01h7hvj14","country_code":"FR","type":"education","lineage":["https://openalex.org/I117841876","https://openalex.org/I2801479458"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cherifa Ben Khelil","raw_affiliation_strings":["EFREI Research Lab, University of Paris Panth\u00e9on Assas, 94800, Villejuif, France","LIFAT, ICVL, University of Tours, 37000, Tours, France","Efrei Research Lab (France)"],"affiliations":[{"raw_affiliation_string":"EFREI Research Lab, University of Paris Panth\u00e9on Assas, 94800, Villejuif, France","institution_ids":["https://openalex.org/I117841876"]},{"raw_affiliation_string":"LIFAT, ICVL, University of Tours, 37000, Tours, France","institution_ids":["https://openalex.org/I4210136805","https://openalex.org/I110017253"]},{"raw_affiliation_string":"Efrei Research Lab (France)","institution_ids":["https://openalex.org/I2801479458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056479939","display_name":"Agata Savary","orcid":"https://orcid.org/0000-0002-6473-6477"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Agata Savary","raw_affiliation_strings":["LISN, University of Paris-Saclay, CNRS, 91400, Orsay, France","STL - Sciences et Technologies des Langues - LISN (France)","LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507\r\nRue du Belv\u00e9d\u00e8re\r\n91405 Orsay cedex\r\net \r\nCampus Universitaire b\u00e2t 640\r\n1 rue Raimond Castaing\r\n91190 Gif-sur-Yvette - France)"],"affiliations":[{"raw_affiliation_string":"LISN, University of Paris-Saclay, CNRS, 91400, Orsay, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"STL - Sciences et Technologies des Langues - LISN (France)","institution_ids":[]},{"raw_affiliation_string":"LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507\r\nRue du Belv\u00e9d\u00e8re\r\n91405 Orsay cedex\r\net \r\nCampus Universitaire b\u00e2t 640\r\n1 rue Raimond Castaing\r\n91190 Gif-sur-Yvette - France)","institution_ids":["https://openalex.org/I4387152856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081958214","display_name":"Iskander Keskes","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119561","display_name":"Digital Research Centre of Sfax","ror":"https://ror.org/02s48dm85","country_code":"TN","type":"facility","lineage":["https://openalex.org/I4210119561"]},{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Iskander Keskes","raw_affiliation_strings":["MIRACL, University of Sfax, 3029, Sfax, Tunisia","MIRACL - Multimedia, InfoRmation systems and Advanced Computing Laboratory (Route de Tunis, km 10, BP 242, Sakiet Ezziet, 3021 SFAX - Tunisia)"],"affiliations":[{"raw_affiliation_string":"MIRACL, University of Sfax, 3029, Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]},{"raw_affiliation_string":"MIRACL - Multimedia, InfoRmation systems and Advanced Computing Laboratory (Route de Tunis, km 10, BP 242, Sakiet Ezziet, 3021 SFAX - Tunisia)","institution_ids":["https://openalex.org/I4210119561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025352510","display_name":"Jean Yves Antoine","orcid":null},"institutions":[{"id":"https://openalex.org/I4387153997","display_name":"Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans","ror":"https://ror.org/01nr3td38","country_code":null,"type":"facility","lineage":["https://openalex.org/I12449238","https://openalex.org/I4210143826","https://openalex.org/I4387153997"]},{"id":"https://openalex.org/I4210136805","display_name":"Laboratoire d'Informatique Fondamentale et Appliqu\u00e9e de Tours","ror":"https://ror.org/03r938j26","country_code":"FR","type":"facility","lineage":["https://openalex.org/I110017253","https://openalex.org/I4210136805"]},{"id":"https://openalex.org/I110017253","display_name":"Universit\u00e9 de Tours","ror":"https://ror.org/02wwzvj46","country_code":"FR","type":"education","lineage":["https://openalex.org/I110017253"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean Yves Antoine","raw_affiliation_strings":["LIFAT, ICVL, University of Tours, 37000, Tours, France","LIFAT - Laboratoire d'Informatique Fondamentale et Appliqu\u00e9e de Tours (64, Avenue Jean Portalis, 37200 Tours - France)","LIFO - Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans (B\u00e2timent IIIA, Rue L\u00e9onard de Vinci, B.P. 6759, F-45067 ORLEANS Cedex 2 - France)"],"affiliations":[{"raw_affiliation_string":"LIFAT, ICVL, University of Tours, 37000, Tours, France","institution_ids":["https://openalex.org/I4210136805","https://openalex.org/I110017253"]},{"raw_affiliation_string":"LIFAT - Laboratoire d'Informatique Fondamentale et Appliqu\u00e9e de Tours (64, Avenue Jean Portalis, 37200 Tours - France)","institution_ids":["https://openalex.org/I4210136805"]},{"raw_affiliation_string":"LIFO - Laboratoire d'Informatique Fondamentale d'Orl\u00e9ans (B\u00e2timent IIIA, Rue L\u00e9onard de Vinci, B.P. 6759, F-45067 ORLEANS Cedex 2 - France)","institution_ids":["https://openalex.org/I4387153997"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001984598","display_name":"Lamia Hadrich Belguith","orcid":"https://orcid.org/0000-0002-4868-657X"},"institutions":[{"id":"https://openalex.org/I4210119561","display_name":"Digital Research Centre of Sfax","ror":"https://ror.org/02s48dm85","country_code":"TN","type":"facility","lineage":["https://openalex.org/I4210119561"]},{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Lamia Belguith Hadrich","raw_affiliation_strings":["MIRACL, University of Sfax, 3029, Sfax, Tunisia","MIRACL - Multimedia, InfoRmation systems and Advanced Computing Laboratory (Route de Tunis, km 10, BP 242, Sakiet Ezziet, 3021 SFAX - Tunisia)"],"affiliations":[{"raw_affiliation_string":"MIRACL, University of Sfax, 3029, Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]},{"raw_affiliation_string":"MIRACL - Multimedia, InfoRmation systems and Advanced Computing Laboratory (Route de Tunis, km 10, BP 242, Sakiet Ezziet, 3021 SFAX - Tunisia)","institution_ids":["https://openalex.org/I4210119561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5032089825"],"corresponding_institution_ids":["https://openalex.org/I110017253","https://openalex.org/I142899784","https://openalex.org/I4210119561","https://openalex.org/I4210136805"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11985207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"59","issue":"2","first_page":"1331","last_page":"1361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9987999796867371,"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/T13629","display_name":"Text Readability and Simplification","score":0.993399977684021,"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/annotation","display_name":"Annotation","score":0.8119089603424072},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.796461820602417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7328577637672424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.676272988319397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5466972589492798},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3341863751411438},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05773186683654785}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8119089603424072},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.796461820602417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7328577637672424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676272988319397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5466972589492798},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3341863751411438},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05773186683654785}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10579-024-09763-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-024-09763-7","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-04738059v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04738059","pdf_url":"https://hal.science/hal-04738059/document","source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Language Resources and Evaluation, 2024, pp.1331-1361. ⟨10.1007/s10579-024-09763-7⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"doi:10.1007/s10579-024-09763-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-024-09763-7","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1410460","https://openalex.org/W134047039","https://openalex.org/W138276892","https://openalex.org/W164170197","https://openalex.org/W2017203275","https://openalex.org/W2114234454","https://openalex.org/W2149279444","https://openalex.org/W2149538544","https://openalex.org/W2150718014","https://openalex.org/W2157514790","https://openalex.org/W2170045142","https://openalex.org/W2250372267","https://openalex.org/W2251062999","https://openalex.org/W2543137198","https://openalex.org/W2574523836","https://openalex.org/W2619927796","https://openalex.org/W2664496537","https://openalex.org/W2793443744","https://openalex.org/W3108096189","https://openalex.org/W4205127277","https://openalex.org/W4283836407","https://openalex.org/W4388130902","https://openalex.org/W4389754673","https://openalex.org/W6600832573","https://openalex.org/W6629641345","https://openalex.org/W6634025009","https://openalex.org/W6804047594","https://openalex.org/W6911778349","https://openalex.org/W6911835389","https://openalex.org/W6949193909"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W4380994516","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,92],"present":[4],"PARSEME-AR,":[5],"the":[6,51,74,88,94,98],"first":[7,95],"openly":[8],"available":[9],"Arabic":[10,53,66,111],"corpus":[11,41],"manually":[12],"annotated":[13],"for":[14,35,97],"Verbal":[15],"Multiword":[16],"Expressions":[17],"(VMWEs).":[18],"The":[19,40,56],"annotation":[20,89],"process":[21],"is":[22],"carried":[23],"out":[24],"based":[25],"on":[26,109],"guidelines":[27],"put":[28],"forward":[29],"by":[30,104],"PARSEME,":[31],"a":[32,60],"multilingual":[33],"project":[34],"more":[36],"than":[37],"26":[38],"languages.":[39],"contains":[42],"4749":[43],"VMWEs":[44,67],"in":[45,65,68,73,102],"about":[46],"7500":[47],"sentences":[48],"taken":[49],"from":[50],"Prague":[52],"Dependency":[54],"Treebank.":[55],"results":[57],"notably":[58],"show":[59],"high":[61],"degree":[62],"of":[63,81],"discontinuity":[64],"comparison":[69],"to":[70],"other":[71],"languages":[72],"PARSEME":[75],"suite.":[76],"We":[77],"also":[78],"propose":[79],"analyses":[80],"interesting":[82],"and":[83],"challenging":[84],"phenomena":[85],"encountered":[86],"during":[87],"process.":[90],"Moreover,":[91],"offer":[93],"benchmark":[96],"VMWE":[99],"identification":[100],"task":[101],"Arabic,":[103],"training":[105],"two":[106],"state-of-the-art":[107],"systems,":[108],"our":[110],"data.":[112]},"counts_by_year":[],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2024-08-29T00:00:00"}