TurkEmbed4Retrieval: Turkish Embedding Model for Retrieval Task

2025/11/10 by Ezerceli, Özay, Gümüşçekiçci, Gizem, Erkoç, Tuğba +1
Computer Science · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Information Retrieval and Search Behavior #Topic Modeling

paper · doi:10.48550/arxiv.2511.07595

openalex publication_date 2025/11/10 · openalex created_date 2025/11/13 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Training Sparse Mixture Of Experts Text Embedding Models
• KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
• mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval
• VNLP: Turkish NLP Package
• 2D Matryoshka Sentence Embeddings
• Multilingual E5 Text Embeddings: A Technical Report
• Developing and Evaluating Tiny to Medium-Sized Turkish BERT Models
• MTEB: Massive Text Embedding Benchmark
• Matryoshka Representation Learning
• ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
• SimCSE: Simple Contrastive Learning of Sentence Embeddings
• Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup
• Fact or Fiction: Verifying Scientific Claims
• ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
• Dense Passage Retrieval for Open-Domain Question Answering
• Unsupervised Cross-lingual Representation Learning at Scale
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• Word Embeddings: A Survey
• Learning Semantic Textual Similarity from Conversations
• GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
• Deep contextualized word representations
• An Overview of Multi-Task Learning in Deep Neural Networks
• Attention Is All You Need
• Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
• A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
• MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
• Enriching Word Vectors with Subword Information
• A large annotated corpus for learning natural language inference
• Efficient Estimation of Word Representations in Vector Space
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• TurkEmbed: Turkish Embedding Model on NLI & STS Tasks
• TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval
• Bridging the Bosphorus: Advancing Turkish Large Language Models through Strategies for Low-Resource Language Adaptation and Benchmarking
• Fine-tuning Transformer-based Encoder for Turkish Language Understanding Tasks
• TRSAv1: A new benchmark dataset for classifying user reviews on Turkish e-commerce websites