{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T03:34:47Z","timestamp":1777952087225,"version":"3.51.4"},"reference-count":27,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"vor","delay-in-days":30,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Procedia Computer Science"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1016\/j.procs.2026.01.048","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T19:30:19Z","timestamp":1774035019000},"page":"393-400","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval"],"prefix":"10.1016","volume":"275","author":[{"given":"\u00d6zay","family":"Ezerceli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahmoud","family":"El Hussieni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Selva","family":"Ta\u015f","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reyhan","family":"Bayraktar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fatma Bet\u00fcl","family":"Terzio\u011flu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuf","family":"\u00c7elebi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya\u011f\u0131z","family":"Asker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.procs.2026.01.048_bib1","doi-asserted-by":"crossref","unstructured":"Karpukhin V, Oguz B, Min S, Lewis P, Wu L, Edunov S, et al. Dense passage retrieval for Open-Domain question answering. EMNLP. 2020 Jan 1; Available from: https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.550","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"10.1016\/j.procs.2026.01.048_bib2","doi-asserted-by":"crossref","unstructured":"Khattab O, Zaharia M. Colbert: Efficient and effective passage search via contextualized late interaction over BERT. In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval 2020 Jul 25 (pp. 39-48).","DOI":"10.1145\/3397271.3401075"},{"key":"10.1016\/j.procs.2026.01.048_bib3","doi-asserted-by":"crossref","unstructured":"Santhanam K, Khattab O, Shaw P, Chang M-W, Zaharia M. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. In:Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL); 2022 May 22\u201327; Dublin, Ireland (Hybrid). Stroudsburg: Association for Computational Linguistics (ACL); 2022. p. 1604\u201317.","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"10.1016\/j.procs.2026.01.048_bib4","doi-asserted-by":"crossref","unstructured":"Formal T, Piwowarski B, Clinchant S. SPLADE: Sparse lexical and expansion model for first-stage ranking. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval; 2021 Jul 11\u201315; Virtual Event. New York (NY): Association for Computing Machinery; 2021. p. 2288\u201392.","DOI":"10.1145\/3404835.3463098"},{"key":"10.1016\/j.procs.2026.01.048_bib5","doi-asserted-by":"crossref","unstructured":"Conneau A, Khandelwal K, Goyal N, Chaudhary V, Wenzek G, Guzm\u00e1n F, Grave E, Ott M, Zettlemoyer L, Stoyanov V. Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116. 2019 Nov 5.","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"10.1016\/j.procs.2026.01.048_bib6","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhang Y, Long D, Xie W, Dai Z, Tang J, Lin H, Yang B, Xie P, Huang F, Zhang M. mgte: Generalized long-context text representation and reranking models for multilingual text retrieval. arXiv preprint arXiv:2407.19669. 2024 Jul 29.","DOI":"10.18653\/v1\/2024.emnlp-industry.103"},{"key":"10.1016\/j.procs.2026.01.048_bib7","unstructured":"Marone M, Weller O, Fleshman W, Yang E, Lawrie D, Van Durme B. mmbert: A modern multilingual encoder with annealed language learning. arXiv preprint arXiv:2509.06888. 2025 Sep 8."},{"key":"10.1016\/j.procs.2026.01.048_bib8","first-page":"14934","article-title":"Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","volume":"33","author":"Wang","year":"2020","journal-title":"Adv Neural Inf Process Syst."},{"key":"10.1016\/j.procs.2026.01.048_bib9","unstructured":"Toprak Kesgin H, Yuce MK, Amasyali MF. Developing and evaluating tiny to medium-sized turkish bert models [Preprint]. 2023. Available from: arXiv:2307.15278"},{"key":"10.1016\/j.procs.2026.01.048_bib10","unstructured":"Weller O, Ricci K, Marone M, Chaffin A, Lawrie D, Van Durme B. Seq vs seq: An open suite of paired encoders and decoders. arXiv preprint arXiv:2507.11412. 2025 Jul 15."},{"key":"10.1016\/j.procs.2026.01.048_bib11","unstructured":"Takehi R, Clavi\u00e9 B, Lee S, Shakir A. Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report. 2025. Available from: https:\/\/arxiv.org\/abs\/2510.14880"},{"key":"10.1016\/j.procs.2026.01.048_bib12","unstructured":"Mezzetti D. Training Tiny Language Models with Token Hashing. NeuML (Medium) https:\/\/neuml.hashnode.dev\/train-a-language-model-from-scratch. 2025"},{"key":"10.1016\/j.procs.2026.01.048_bib13","unstructured":"Budur E, \u00d6z\u00e7elik R, G\u00fcng\u00f6r T, Potts C. Data and representation for Turkish natural language inference. arXiv preprint arXiv:2004.14963.2020 Apr 30."},{"key":"10.1016\/j.procs.2026.01.048_bib14","doi-asserted-by":"crossref","unstructured":"Beken Fikri F, Oflazer K, Yanikoglu B. Semantic Similarity Based Evaluation for Abstractive News Summarization. In: Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021); 2021 Nov 10; Punta Cana, Dominican Republic. Stroudsburg: Association for Computational Linguistics (ACL); 2021. p. 24\u201333.","DOI":"10.18653\/v1\/2021.gem-1.3"},{"key":"10.1016\/j.procs.2026.01.048_bib15","doi-asserted-by":"crossref","unstructured":"Chaffin A, Sourty R. Pylate: Flexible training and retrieval for late interaction models. arXiv preprint arXiv:2508.03555. 2025 Aug 5.","DOI":"10.1145\/3746252.3761608"},{"key":"10.1016\/j.procs.2026.01.048_bib16","unstructured":"Parsak A, et al. MS MARCO-TR:A Turkish Adaptation of the MS MARCO Passage Ranking Dataset. Hugging Face Dataset. 2024. Available from: https:\/\/huggingface.co\/datasets\/parsak\/msmarco-tr."},{"key":"10.1016\/j.procs.2026.01.048_bib17","unstructured":"Biewald L. Experiment Tracking with Weights and Biases. [Internet]. 2020. Available from: https:\/\/www.wandb.com\/."},{"key":"10.1016\/j.procs.2026.01.048_bib18","unstructured":"Saoud A. scifact-tr: Turkish translation of SciFact for fact-checking & retrieval. Hugging Face Datasets Repository [Internet]. 2024. Available from: https:\/\/huggingface.co\/datasets\/AbdulkaderSaoud\/scifact-tr."},{"key":"10.1016\/j.procs.2026.01.048_bib19","unstructured":"trmteb. arguana-tr: Turkish version of the ArguAna argument retrieval dataset. Hugging Face dataset [Internet]. 2025. Available from: https:\/\/huggingface.co\/datasets\/trmteb\/arguana-tr."},{"key":"10.1016\/j.procs.2026.01.048_bib20","unstructured":"trmteb. fiqa-tr: Turkish financial question answering dataset. Hugging Face dataset [Internet]. 2025. Available from: https:\/\/huggingface.co\/datasets\/trmteb\/fiqa-tr."},{"key":"10.1016\/j.procs.2026.01.048_bib21","unstructured":"trmteb. scidocs-tr: Turkish version of the SciDocs dataset as part of the TR-MTEB benchmark. Hugging Face dataset. 2025. Available from:https:\/\/huggingface.co\/datasets\/trmteb\/scidocs-tr."},{"key":"10.1016\/j.procs.2026.01.048_bib22","unstructured":"trmteb. nfcorpus-tr: Turkish translation of the NF Corpus for nutrition-focused retrieval. Hugging Face dataset. 2025. Available from: https:\/\/huggingface.co\/datasets\/trmteb\/nfcorpus-tr."},{"key":"10.1016\/j.procs.2026.01.048_bib23","doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I. Sentence-BERT:Sentence Embeddings using Siamese BERT-Networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP);2019 Nov 3\u20137;Hong Kong, China. Stroudsburg:Association for Computational Linguistics (ACL);2019. p. 3982\u201392.","DOI":"10.18653\/v1\/D19-1410"},{"key":"10.1016\/j.procs.2026.01.048_bib24","doi-asserted-by":"crossref","unstructured":"Jayaram R, Dhulipala L, Hadian M, Lee JD, Mirrokni V. MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding. Advances in Neural Information Processing Systems. 2024 Dec 16;37:101042-73.","DOI":"10.52202\/079017-3204"},{"key":"10.1016\/j.procs.2026.01.048_bib25","series-title":"TurkEmbed4Retrieval: Turkish Embedding Model for Retrieval Task. In 2025 33rd Signal Processing and Communications Applications Conference (SIU) 2025 Jun 25 (pp. 1-4)","author":"\u00d6","year":"2025"},{"key":"10.1016\/j.procs.2026.01.048_bib26","doi-asserted-by":"crossref","unstructured":"Santhanam K, Khattab O, Potts C, Zaharia M. PLAID: An efficient engine for late interaction retrieval. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management (CIKM); 2022 Oct 17\u201321; Atlanta, Georgia, USA. New York: Association for Computing Machinery (ACM); 2022. p. 1747\u201356.","DOI":"10.1145\/3511808.3557325"},{"key":"10.1016\/j.procs.2026.01.048_bib27","unstructured":"Thakur N, Reimers N, R\u00fcckle A, Srivastava A, Gurevych I. BEIR:A heterogenous benchmark for zero-shot evaluation of information retrieval models [Preprint]. 2021. Available from: arXiv:2104.08663"}],"container-title":["Procedia Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050926000487?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050926000487?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T11:28:38Z","timestamp":1777894118000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1877050926000487"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":27,"alternative-id":["S1877050926000487"],"URL":"https:\/\/doi.org\/10.1016\/j.procs.2026.01.048","relation":{},"ISSN":["1877-0509"],"issn-type":[{"value":"1877-0509","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval","name":"articletitle","label":"Article Title"},{"value":"Procedia Computer Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.procs.2026.01.048","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}]}}