{"id":"https://openalex.org/W7135408039","doi":"https://doi.org/10.1007/s10579-025-09876-7","title":"Towards a resource for multilingual lexicons: an MT assisted and human-in-the-loop multilingual parallel corpus with multi-word expression annotation","display_name":"Towards a resource for multilingual lexicons: an MT assisted and human-in-the-loop multilingual parallel corpus with multi-word expression annotation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7135408039","doi":"https://doi.org/10.1007/s10579-025-09876-7","pmid":"https://pubmed.ncbi.nlm.nih.gov/41841126"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-025-09876-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-025-09876-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09876-7.pdf","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09876-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129255086","display_name":"Lifeng Han","orcid":null},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]},{"id":"https://openalex.org/I210716285","display_name":"University of Applied Sciences Leiden","ror":"https://ror.org/0093src13","country_code":"NL","type":"education","lineage":["https://openalex.org/I210716285"]},{"id":"https://openalex.org/I2800006345","display_name":"Leiden University Medical Center","ror":"https://ror.org/05xvt9f17","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800006345"]},{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB","NL"],"is_corresponding":true,"raw_author_name":"Lifeng Han","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, NL The Netherlands","Leiden University Medical Center, Leiden University, Leiden, NL The Netherlands","University of Manchester, Manchester, M13 9PL UK"],"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, NL The Netherlands","institution_ids":["https://openalex.org/I121797337","https://openalex.org/I210716285"]},{"raw_affiliation_string":"Leiden University Medical Center, Leiden University, Leiden, NL The Netherlands","institution_ids":["https://openalex.org/I2800006345"]},{"raw_affiliation_string":"University of Manchester, Manchester, M13 9PL UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129150254","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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Najet Hadj Mohamed","raw_affiliation_strings":["University of Tours, France and Arabic Natural Language Processing Research Group, University of Sfax, Tours, France"],"affiliations":[{"raw_affiliation_string":"University of Tours, France and Arabic Natural Language Processing Research Group, University of Sfax, Tours, France","institution_ids":["https://openalex.org/I110017253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096196655","display_name":"Malak Rassem","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Malak Rassem","raw_affiliation_strings":["Institute for Natural Language Processing (IMS), University of Stuttgart, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018481328","display_name":"Gareth J. F. Jones","orcid":"https://orcid.org/0000-0003-2923-8365"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Gareth J. F. Jones","raw_affiliation_strings":["ADAPT Research Centre, Dublin City University, Dublin 9, Ireland"],"affiliations":[{"raw_affiliation_string":"ADAPT Research Centre, Dublin City University, Dublin 9, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008334059","display_name":"Alan F. Smeaton","orcid":"https://orcid.org/0000-0003-1028-8389"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Alan F. Smeaton","raw_affiliation_strings":["Insight Centre for Data Analytics, Dublin City University, Dublin 9, Ireland"],"affiliations":[{"raw_affiliation_string":"Insight Centre for Data Analytics, Dublin City University, Dublin 9, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005912060","display_name":"Goran Nenadi\u0107","orcid":"https://orcid.org/0000-0003-0795-5363"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Goran Nenadic","raw_affiliation_strings":["University of Manchester, Manchester, M13 9PL UK"],"affiliations":[{"raw_affiliation_string":"University of Manchester, Manchester, M13 9PL UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129255086"],"corresponding_institution_ids":["https://openalex.org/I121797337","https://openalex.org/I210716285","https://openalex.org/I2800006345","https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82444682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"60","issue":"2","first_page":"33","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9061999917030334,"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":0.9061999917030334,"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/T10759","display_name":"Translation Studies and Practices","score":0.03959999978542328,"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/T13629","display_name":"Text Readability and Simplification","score":0.008799999952316284,"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":0.7990000247955322},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7045000195503235},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6202999949455261},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4968999922275543},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42989999055862427},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4156999886035919},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.3587999939918518},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.34450000524520874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8179000020027161},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7990000247955322},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7472000122070312},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7045000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6790000200271606},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6202999949455261},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4968999922275543},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42989999055862427},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3587999939918518},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.3167000114917755},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s10579-025-09876-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-025-09876-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09876-7.pdf","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":"pmid:41841126","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41841126","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language resources and evaluation","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12989027","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12989027/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lang Resour Eval","raw_type":"Text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/9f9c36b2-81ef-4120-b4df-eee5538b069f","is_oa":true,"landing_page_url":"https://link.springer.com/10.1007/s10579-025-09876-7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Han, L, Mohamed, N H, Rassem, M, Jones, G J F, Smeaton, A F & Nenadic, G 2026, 'Towards a resource for multilingual lexicons: an MT assisted and human-in-the-loop multilingual parallel corpus with multi-word expression annotation', Language Resources and Evaluation, vol. 60, no. 2. https://doi.org/10.1007/s10579-025-09876-7","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:publications/9f9c36b2-81ef-4120-b4df-eee5538b069f","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/9f9c36b2-81ef-4120-b4df-eee5538b069f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Han, L, Mohamed, N H, Rassem, M, Jones, G J F, Smeaton, A F & Nenadic, G 2026, 'Towards a resource for multilingual lexicons: an MT assisted and human-in-the-loop multilingual parallel corpus with multi-word expression annotation', Language Resources and Evaluation, vol. 60, no. 2. https://doi.org/10.1007/s10579-025-09876-7","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1007/s10579-025-09876-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-025-09876-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09876-7.pdf","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":[{"score":0.7619872093200684,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1383882326","display_name":null,"funder_award_id":"SFI/12/RC/","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G2881606312","display_name":null,"funder_award_id":"SFI/12/RC/2289","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G3989894238","display_name":null,"funder_award_id":"12/RC/2289","funder_id":"https://openalex.org/F4320331354","funder_display_name":"Insight SFI Research Centre for Data Analytics"},{"id":"https://openalex.org/G3993907298","display_name":null,"funder_award_id":"13/RC/2106","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G5098725405","display_name":null,"funder_award_id":"12/RC/","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G6712843611","display_name":null,"funder_award_id":"12/RC/228","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G694931829","display_name":"Integrating hospital outpatient letters into the healthcare data space","funder_award_id":"EP/V047949/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7362007176","display_name":null,"funder_award_id":"12/RC/2289","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G8001517797","display_name":null,"funder_award_id":"SFI/12/RC/2289","funder_id":"https://openalex.org/F4320331354","funder_display_name":"Insight SFI Research Centre for Data Analytics"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320331354","display_name":"Insight SFI Research Centre for Data Analytics","ror":null},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7135408039.pdf","grobid_xml":"https://content.openalex.org/works/W7135408039.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2161895154","https://openalex.org/W2550821151","https://openalex.org/W2563048171","https://openalex.org/W2610162951","https://openalex.org/W2610359288","https://openalex.org/W2619927796","https://openalex.org/W2664496537","https://openalex.org/W2785406690","https://openalex.org/W2970947975","https://openalex.org/W3013197936","https://openalex.org/W3091307578","https://openalex.org/W3108362930"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,103],"work,":[2],"we":[3,172,196,228],"introduce":[4],"the":[5,34,43,46,72,92,161,177,217,230],"construction":[6],"of":[7,20,45,70,102,112,141,151,163,176,193,216],"a":[8,40,135,174,190],"machine":[9,100],"translation":[10,101,150,220],"(MT)":[11],"assisted":[12],"and":[13,55,68,78,83,110,132,212,222,241,250],"human-in-the-loop":[14,164],"multilingual":[15],"parallel":[16],"corpus":[17,74,88,105],"with":[18],"annotations":[19],"multi-word":[21,246],"expressions":[22],"(MWEs),":[23],"named":[24],"AlphaMWE.":[25],"The":[26,49,59],"MWEs":[27,30,152],"include":[28,62],"verbal":[29],"(vMWEs)":[31],"defined":[32],"in":[33,96,184],"PARSEME":[35,93],"shared":[36,94],"task":[37,95],"that":[38,148],"have":[39],"verb":[41],"as":[42,158,245],"head":[44],"studied":[47],"terms.":[48],"annotated":[50],"vMWEs":[51],"are":[52],"also":[53],"bilingually":[54],"multilingually":[56],"aligned":[57],"manually.":[58],"languages":[60],"covered":[61],"Arabic,":[63],"Chinese,":[64],"English,":[65],"German,":[66],"Italian,":[67],"Polish,":[69],"which,":[71],"Arabic":[73],"includes":[75],"both":[76,239],"standard":[77],"dialectal":[79],"variations":[80],"from":[81,91],"Egypt":[82],"Tunisia.":[84],"Our":[85],"original":[86],"English":[87],"is":[89,147],"taken":[90],"2018.":[97],"We":[98],"performed":[99],"source":[104],"followed":[106],"by":[107,160,181,225],"human":[108,226],"post-editing":[109,131],"annotation":[111,133,224],"target":[113],"MWEs.":[114],"Strict":[115],"quality":[116,138],"control":[117],"was":[118],"applied":[119],"for":[120,203,238],"error":[121,178],"limitation,":[122],"i.e.,":[123],"each":[124],"MT":[125,156,170,182,194,201],"output":[126],"sentence":[127],"received":[128],"first":[129],"manual":[130,137],"plus":[134],"second":[136],"rechecking.":[139],"One":[140],"our":[142],"findings":[143],"during":[144],"corpora":[145],"preparation":[146],"accurate":[149],"presents":[153],"challenges":[154],"to":[155],"systems,":[157],"reflected":[159],"outcomes":[162],"metric":[165],"HOPE.":[166],"To":[167,188],"facilitate":[168],"further":[169],"research,":[171,243],"present":[173],"categorisation":[175],"types":[179],"encountered":[180],"systems":[183,202],"performing":[185],"MWE-related":[186],"translation.":[187],"acquire":[189],"broader":[191],"view":[192],"issues,":[195],"selected":[197],"four":[198],"popular":[199],"state-of-the-art":[200],"comparison,":[204],"namely":[205],"Microsoft":[206],"Bing":[207],"Translator,":[208],"GoogleMT,":[209],"Baidu":[210],"Fanyi,":[211],"DeepL":[213],"MT.":[214],"Because":[215],"noise":[218],"removal,":[219],"post-editing,":[221],"MWE":[223],"professionals,":[227],"believe":[229],"AlphaMWE":[231],"data":[232],"set":[233],"will":[234],"be":[235],"an":[236],"asset":[237],"monolingual":[240],"cross-lingual":[242],"such":[244],"term":[247],"lexicography,":[248],"MT,":[249],"information":[251],"extraction.":[252]},"counts_by_year":[],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2026-03-15T00:00:00"}
