TurkEmbed: Turkish Embedding Model on NLI & STS Tasks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911259577810944 |
|---|---|
| author | Ezerceli, Özay Gümüşçekiçci, Gizem Erkoç, Tuğba Özenç, Berke |
| author_facet | Ezerceli, Özay Gümüşçekiçci, Gizem Erkoç, Tuğba Özenç, Berke |
| contents | This paper introduces TurkEmbed, a novel Turkish language embedding model designed to outperform existing models, particularly in Natural Language Inference (NLI) and Semantic Textual Similarity (STS) tasks. Current Turkish embedding models often rely on machine-translated datasets, potentially limiting their accuracy and semantic understanding. TurkEmbed utilizes a combination of diverse datasets and advanced training techniques, including matryoshka representation learning, to achieve more robust and accurate embeddings. This approach enables the model to adapt to various resource-constrained environments, offering faster encoding capabilities. Our evaluation on the Turkish STS-b-TR dataset, using Pearson and Spearman correlation metrics, demonstrates significant improvements in semantic similarity tasks. Furthermore, TurkEmbed surpasses the current state-of-the-art model, Emrecan, on All-NLI-TR and STS-b-TR benchmarks, achieving a 1-4\% improvement. TurkEmbed promises to enhance the Turkish NLP ecosystem by providing a more nuanced understanding of language and facilitating advancements in downstream applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08376 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TurkEmbed: Turkish Embedding Model on NLI & STS Tasks Ezerceli, Özay Gümüşçekiçci, Gizem Erkoç, Tuğba Özenç, Berke Computation and Language Information Retrieval This paper introduces TurkEmbed, a novel Turkish language embedding model designed to outperform existing models, particularly in Natural Language Inference (NLI) and Semantic Textual Similarity (STS) tasks. Current Turkish embedding models often rely on machine-translated datasets, potentially limiting their accuracy and semantic understanding. TurkEmbed utilizes a combination of diverse datasets and advanced training techniques, including matryoshka representation learning, to achieve more robust and accurate embeddings. This approach enables the model to adapt to various resource-constrained environments, offering faster encoding capabilities. Our evaluation on the Turkish STS-b-TR dataset, using Pearson and Spearman correlation metrics, demonstrates significant improvements in semantic similarity tasks. Furthermore, TurkEmbed surpasses the current state-of-the-art model, Emrecan, on All-NLI-TR and STS-b-TR benchmarks, achieving a 1-4\% improvement. TurkEmbed promises to enhance the Turkish NLP ecosystem by providing a more nuanced understanding of language and facilitating advancements in downstream applications. |
| title | TurkEmbed: Turkish Embedding Model on NLI & STS Tasks |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2511.08376 |