{"id":"https://openalex.org/W4416034623","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.471","title":"TR-MTEB: A Comprehensive Benchmark and Embedding Model Suite for Turkish Sentence Representations","display_name":"TR-MTEB: A Comprehensive Benchmark and Embedding Model Suite for Turkish Sentence Representations","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034623","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.471"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.471","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.471","pdf_url":"https://aclanthology.org/2025.findings-emnlp.471.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":"Findings of the Association for Computational Linguistics: EMNLP 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.findings-emnlp.471.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072237433","display_name":"Mehmet Baysan","orcid":"https://orcid.org/0000-0001-7359-2965"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehmet Selman Baysan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5030496360","display_name":"Tunga G\u00fcng\u00f6r","orcid":"https://orcid.org/0000-0001-9448-9422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tunga Gungor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86983204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8867","last_page":"8887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.20059999823570251,"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":0.20059999823570251,"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":0.1753000020980835,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.1462000012397766,"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/suite","display_name":"Suite","score":0.6603000164031982},{"id":"https://openalex.org/keywords/turkish","display_name":"Turkish","score":0.6123999953269958},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5374000072479248},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5023000240325928},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4894999861717224}],"concepts":[{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6603000164031982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6579999923706055},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.6123999953269958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5633000135421753},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5199000239372253},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4894999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.263700008392334},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.471","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.471","pdf_url":"https://aclanthology.org/2025.findings-emnlp.471.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.471","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.471","pdf_url":"https://aclanthology.org/2025.findings-emnlp.471.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034623.pdf","grobid_xml":"https://content.openalex.org/works/W4416034623.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"TR-MTEB,":[2],"the":[3],"first":[4],"large-scale,":[5],"task-diverse":[6],"benchmark":[7],"designed":[8],"to":[9,101],"evaluate":[10],"sentence":[11,54],"embedding":[12,60],"models":[13,61],"for":[14],"Turkish.Covering":[15],"six":[16],"core":[17],"tasks":[18,84],"as":[19],"classification,":[20,23],"clustering,":[21],"pair":[22],"retrieval,":[24],"bitext":[25],"mining,":[26],"and":[27,38,56,65,85,94,110],"semantic":[28],"textual":[29],"similarity,":[30],"TR-MTEB":[31],"incorporates":[32],"26":[33],"high-quality":[34],"datasets,":[35,92],"including":[36],"native":[37],"translated":[39],"resources.To":[40],"complement":[41],"this":[42],"benchmark,":[43],"we":[44],"construct":[45],"a":[46],"corpus":[47],"of":[48],"34.2":[49],"million":[50],"weakly":[51],"supervised":[52,66],"Turkish":[53,106],"pairs":[55],"train":[57],"two":[58],"Turkish-specific":[59],"using":[62],"contrastive":[63],"pretraining":[64],"fine-tuning.Evaluation":[67],"results":[68],"show":[69],"that":[70],"our":[71],"models,":[72,93],"despite":[73],"being":[74],"trained":[75],"on":[76],"limited":[77],"resources,":[78],"achieve":[79],"competitive":[80],"performance":[81],"across":[82],"most":[83],"significantly":[86],"improve":[87],"upon":[88],"baseline":[89],"monolingual":[90],"models.All":[91],"evaluation":[95],"pipelines":[96],"are":[97],"publicly":[98],"released":[99],"1":[100],"facilitate":[102],"further":[103],"research":[104],"in":[105],"natural":[107],"language":[108],"processing":[109],"low-resource":[111],"benchmarking.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}