{"id":"https://openalex.org/W4415315375","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1236","title":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","display_name":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415315375","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1236"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1236","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1236","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1236","pdf_url":"https://aclanthology.org/2026.findings-acl.1236.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-acl.1236.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004688187","display_name":"Nikolay Banar","orcid":"https://orcid.org/0000-0001-9517-5791","observed_orcids":["https://orcid.org/0000-0001-9517-5791"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nikolay Banar","raw_affiliation_strings":["University of Antwerp , Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp , Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046964566","display_name":"Ehsan Lotfi","orcid":"https://orcid.org/0000-0001-6427-0825","observed_orcids":["https://orcid.org/0000-0001-6427-0825"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ehsan Lotfi","raw_affiliation_strings":["University of Antwerp , Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp , Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090129146","display_name":"Jens Van Nooten","orcid":"https://orcid.org/0000-0002-0165-5709","observed_orcids":["https://orcid.org/0000-0002-0165-5709"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jens Van Nooten","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017673354","display_name":"Cristina Arhiliuc","orcid":"https://orcid.org/0000-0002-5352-206X","observed_orcids":["https://orcid.org/0000-0002-5352-206X"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Cristina Arhiliuc","raw_affiliation_strings":["University of Antwerp , Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp , Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120049377","display_name":"Marija Kliocaite","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Marija Kliocaite","raw_affiliation_strings":["University of Antwerp , Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp , Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083411784","display_name":"Walter M. P. Daelemans","orcid":"https://orcid.org/0000-0002-9832-7890","observed_orcids":["https://orcid.org/0000-0002-9832-7890"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Walter Daelemans","raw_affiliation_strings":["University of Antwerp , Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp , Belgium","institution_ids":["https://openalex.org/I149213910"]}]}],"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":0.01128155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24684","last_page":"24709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9970999956130981,"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/T10028","display_name":"Topic Modeling","score":0.9970999956130981,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/dutch","display_name":"Dutch language","score":0.828000009059906},{"id":"https://openalex.org/keywords/text-embeddings","display_name":"text embeddings","score":0.765999972820282},{"id":"https://openalex.org/keywords/multilingual-word-embeddings","display_name":"multilingual embeddings","score":0.5770000219345093},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.5320000052452087},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.843999981880188},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.5920000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419000267982483},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7332000136375427},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7257000207901001},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6528000235557556},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.48249998688697815},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4438000023365021},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37549999356269836},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35010001063346863},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3398999869823456},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32120001316070557},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1236","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1236","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1236","pdf_url":"https://aclanthology.org/2026.findings-acl.1236.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.12340","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12340","pdf_url":"https://arxiv.org/pdf/2509.12340","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.12340","doi":"https://doi.org/10.48550/arxiv.2509.12340","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.12340","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1236","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1236","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1236","pdf_url":"https://aclanthology.org/2026.findings-acl.1236.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415315375.pdf","grobid_xml":"https://content.openalex.org/works/W4415315375.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4377865016","https://openalex.org/W4389520682","https://openalex.org/W7131825942","https://openalex.org/W4390092262","https://openalex.org/W4416034623","https://openalex.org/W7070309442","https://openalex.org/W7134062012","https://openalex.org/W2460747544","https://openalex.org/W7212461400","https://openalex.org/W4397028511"],"abstract_inverted_index":{"Recently,":[0],"embedding":[1,115],"resources,":[2],"including":[3],"models,":[4],"benchmarks,":[5],"and":[6,37,52,70,134],"datasets,":[7,90],"have":[8],"been":[9],"widely":[10],"released":[11],"to":[12,100],"support":[13],"a":[14,26,75,82,108],"variety":[15],"of":[16,29,42,78,110],"languages.However,":[17],"the":[18,30,39,56,130,135],"Dutch":[19,43,62,68,88],"language":[20,98],"remains":[21],"underrepresented,":[22],"typically":[23],"comprising":[24],"only":[25],"small":[27],"fraction":[28],"published":[31],"multilingual":[32],"resources.To":[33],"address":[34],"this":[35],"gap":[36],"encourage":[38],"further":[40],"development":[41],"embeddings,":[44],"we":[45,54,80,106],"introduce":[46,55],"new":[47],"resources":[48,126],"for":[49,61],"their":[50],"evaluation":[51],"generation.First,":[53],"Massive":[57],"Text":[58],"Embedding":[59],"Benchmark":[60],"(MTEB-NL),":[63],"which":[64],"includes":[65],"both":[66],"existing":[67],"datasets":[69],"newly":[71],"created":[72],"ones,":[73],"covering":[74],"wide":[76],"range":[77],"tasks.Second,":[79],"provide":[81],"training":[83],"dataset":[84],"compiled":[85],"from":[86],"available":[87,128],"retrieval":[89],"complemented":[91],"with":[92],"synthetic":[93],"data":[94],"generated":[95],"by":[96],"large":[97],"models":[99,116],"expand":[101],"task":[102],"coverage":[103],"beyond":[104],"retrieval.Finally,":[105],"release":[107],"series":[109],"E5-NL":[111],"compact":[112],"yet":[113],"efficient":[114],"that":[117],"demonstrate":[118],"strong":[119],"performance":[120],"across":[121],"multiple":[122],"tasks.We":[123],"make":[124],"our":[125],"publicly":[127],"through":[129],"Hugging":[131],"Face":[132],"Hub":[133],"MTEB":[136],"package.":[137]},"counts_by_year":[],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2025-10-18T00:00:00"}
