In this work, we introduce TurkEmbed4Retrieval, a retrieval specialized variant of the TurkEmbed model originally designed for Natural Language Inference (NLI) and Semantic Textual Similarity (STS) tasks. By fine-tuning the base model on the MS MARCO TR dataset using advanced training techniques, including Matryoshka representation learning and a tailored multiple negatives ranking loss, we achieve SOTA performance for Turkish retrieval tasks. Extensive experiments demonstrate that our model outperforms Turkish colBERT by 19,26% on key retrieval metrics for the Scifact TR dataset, thereby establishing a new benchmark for Turkish information retrieval.
@article{arxiv.2511.07595,
title = {TurkEmbed4Retrieval: Turkish Embedding Model for Retrieval Task},
author = {Özay Ezerceli and Gizem Gümüşçekiçci and Tuğba Erkoç and Berke Özenç},
journal= {arXiv preprint arXiv:2511.07595},
year = {2025}
}
Comments
4 pages, in Turkish language, 1 figure, conference