TurkEmbed4Retrieval: Turkish Embedding Model for Retrieval Task
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911258561740800 |
|---|---|
| author | Ezerceli, Özay Gümüşçekiçci, Gizem Erkoç, Tuğba Özenç, Berke |
| author_facet | Ezerceli, Özay Gümüşçekiçci, Gizem Erkoç, Tuğba Özenç, Berke |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07595 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TurkEmbed4Retrieval: Turkish Embedding Model for Retrieval Task Ezerceli, Özay Gümüşçekiçci, Gizem Erkoç, Tuğba Özenç, Berke Information Retrieval 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. |
| title | TurkEmbed4Retrieval: Turkish Embedding Model for Retrieval Task |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2511.07595 |