{"id":"https://openalex.org/W7140132489","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.86","title":"VN-MTEB: Vietnamese Massive Text Embedding Benchmark","display_name":"VN-MTEB: Vietnamese Massive Text Embedding Benchmark","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140132489","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.86"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.86","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.86","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.86","pdf_url":"https://aclanthology.org/2026.findings-eacl.86.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","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: EACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-eacl.86.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130347844","display_name":"Loc Pham","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Loc Pham","raw_affiliation_strings":["School of Electrical Engineering , International University , VNU-HCMC , Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering , International University , VNU-HCMC , Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076276387","display_name":"Tung Van Luu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tung Luu","raw_affiliation_strings":["School of Electrical Engineering , International University , VNU-HCMC , Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering , International University , VNU-HCMC , Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130365244","display_name":"Thu Vo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thu Vo","raw_affiliation_strings":["School of Electrical Engineering , International University , VNU-HCMC , Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering , International University , VNU-HCMC , Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130381845","display_name":"Minh Cong Nguyen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Minh Nguyen","raw_affiliation_strings":["School of Electrical Engineering , International University , VNU-HCMC , Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering , International University , VNU-HCMC , Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133951425","display_name":"Viet Hoang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Viet Hoang","raw_affiliation_strings":["School of Electrical Engineering , International University , VNU-HCMC , Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering , International University , VNU-HCMC , Vietnam","institution_ids":["https://openalex.org/I123565023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123565023"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15055351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1705","last_page":"1725"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9911999702453613,"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":0.9911999702453613,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.0015999999595806003,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.0010000000474974513,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/text-embeddings","display_name":"text embeddings","score":0.8769999742507935},{"id":"https://openalex.org/keywords/vietnamese-language","display_name":"Vietnamese language","score":0.6190000176429749},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.7200000286102295},{"id":"https://openalex.org/keywords/online-toxicity","display_name":"online toxicity","score":0.7639999985694885},{"id":"https://openalex.org/keywords/content-moderation","display_name":"content moderation","score":0.6359999775886536},{"id":"https://openalex.org/keywords/recommender-systems","display_name":"recommender systems","score":0.8939999938011169},{"id":"https://openalex.org/keywords/rotary-positional-embeddings","display_name":"rotary positional embeddings","score":0.9380000233650208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.670799970626831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5224000215530396},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3763999938964844},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25029999017715454},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.86","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.86","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.86","pdf_url":"https://aclanthology.org/2026.findings-eacl.86.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","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: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.86","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.86","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.86","pdf_url":"https://aclanthology.org/2026.findings-eacl.86.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140132489.pdf","grobid_xml":"https://content.openalex.org/works/W7140132489.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4386576685","https://openalex.org/W7140100985","https://openalex.org/W7171591496","https://openalex.org/W7167572859","https://openalex.org/W3190613055","https://openalex.org/W4396821944","https://openalex.org/W4415947158","https://openalex.org/W7212461400","https://openalex.org/W3005664898","https://openalex.org/W6966621971"],"abstract_inverted_index":{"Vietnam":[0],"ranks":[1],"among":[2],"the":[3],"top":[4],"countries":[5],"in":[6,26,37,55,88],"terms":[7],"of":[8,32],"both":[9,36],"internet":[10],"traffic":[11],"and":[12,22,39,74],"online":[13],"toxicity.As":[14],"a":[15,30,65],"result,":[16],"implementing":[17],"embedding":[18,89],"models":[19,51,77],"for":[20,45],"recommendation":[21],"content":[23],"control":[24],"duties":[25],"applications":[27],"is":[28],"crucial.However,":[29],"lack":[31],"large-scale":[33,57],"test":[34],"datasets,":[35],"volume":[38],"task":[40],"diversity,":[41],"makes":[42],"it":[43],"tricky":[44],"scientists":[46],"to":[47],"effectively":[48],"evaluate":[49],"AI":[50],"before":[52],"deploying":[53],"them":[54],"real-world,":[56],"projects.To":[58],"solve":[59],"this":[60],"important":[61],"problem,":[62],"we":[63,70],"introduce":[64],"text":[66],"embeddings.In":[67],"our":[68],"analysis,":[69],"find":[71],"that":[72],"bigger":[73],"more":[75],"complex":[76],"using":[78,84],"Rotary":[79],"Positional":[80,86],"Embedding":[81,87],"outperform":[82],"those":[83],"Absolute":[85],"tasks.":[90]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}
