SindBERT, the Sailor: Charting the Seas of Turkish NLP

• URL: http://arxiv.org/abs/2510.21364v1
• Date: Fri, 24 Oct 2025 11:48:49 GMT
• Title: SindBERT, the Sailor: Charting the Seas of Turkish NLP
• Authors: Raphael Scheible-Schmitt, Stefan Schweter,
• Abstract summary: SindBERT is trained from scratch on 312 GB of Turkish text.<n>We evaluate SindBERT on part-of-speech tagging, named entity recognition, offensive language detection, and the TurBLiMP linguistic acceptability benchmark.
• Score: 0.05570276034354691
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformer models have revolutionized NLP, yet many morphologically rich languages remain underrepresented in large-scale pre-training efforts. With SindBERT, we set out to chart the seas of Turkish NLP, providing the first large-scale RoBERTa-based encoder for Turkish. Trained from scratch on 312 GB of Turkish text (mC4, OSCAR23, Wikipedia), SindBERT is released in both base and large configurations, representing the first large-scale encoder-only language model available for Turkish. We evaluate SindBERT on part-of-speech tagging, named entity recognition, offensive language detection, and the TurBLiMP linguistic acceptability benchmark. Our results show that SindBERT performs competitively with existing Turkish and multilingual models, with the large variant achieving the best scores in two of four tasks but showing no consistent scaling advantage overall. This flat scaling trend, also observed for XLM-R and EuroBERT, suggests that current Turkish benchmarks may already be saturated. At the same time, comparisons with smaller but more curated models such as BERTurk highlight that corpus quality and diversity can outweigh sheer data volume. Taken together, SindBERT contributes both as an openly released resource for Turkish NLP and as an empirical case study on the limits of scaling and the central role of corpus composition in morphologically rich languages. The SindBERT models are released under the MIT license and made available in both fairseq and Huggingface formats.

Related papers

• TabiBERT: A Large-Scale ModernBERT Foundation Model and A Unified Benchmark for Turkish [0.7233065479782755]
  TabiBERT is a monolingual Turkish encoder based on ModernBERT architecture trained from scratch on a large, curated corpus.<n>It supports 8,192-token context length (16x original BERT), achieves up to 2.65x speedup, and reduces GPU memory consumption.<n>It attains 77.58 on TabiBench, outperforming BERTurk by 1.62 points and establishing state-of-the-art on five of eight categories.
  arXiv  Detail & Related papers  (2025-12-28T20:18:22Z)
• Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications [0.0]
  This paper introduces Turk-LettuceDetect, the first suite of hallucination detection models specifically designed for Turkish RAG applications.<n>These models were trained on a machine-translated version of the RAGTruth benchmark dataset containing 17,790 instances across question answering, data-to-text generation, and summarization tasks.<n>Our experimental results show that the ModernBERT-based model achieves an F1-score of 0.7266 on the complete test set, with particularly strong performance on structured tasks.
  arXiv  Detail & Related papers  (2025-09-22T12:14:11Z)
• mmBERT: A Modern Multilingual Encoder with Annealed Language Learning [57.58071656545661]
  mmBERT is an encoder-only language model pretrained on 3T tokens of multilingual text.<n>We add over 1700 low-resource languages to the data mix only during the decay phase.<n>We show that mmBERT significantly outperforms the previous generation of models on classification and retrieval tasks.
  arXiv  Detail & Related papers  (2025-09-08T17:08:42Z)
• TurkishBERTweet: Fast and Reliable Large Language Model for Social Media Analysis [4.195270491854775]
  We introduce TurkishBERTweet, the first large scale pre-trained language model for Turkish social media built using almost 900 million tweets. The model shares the same architecture as base BERT model with smaller input length, making TurkishBERTweet lighter than BERTurk. We demonstrate that TurkishBERTweet outperforms the other available alternatives on generalizability and its lower inference time gives significant advantage to process large-scale datasets.
  arXiv  Detail & Related papers  (2023-11-29T20:22:44Z)
• Cross-Lingual NER for Financial Transaction Data in Low-Resource Languages [70.25418443146435]
  We propose an efficient modeling framework for cross-lingual named entity recognition in semi-structured text data. We employ two independent datasets of SMSs in English and Arabic, each carrying semi-structured banking transaction information. With access to only 30 labeled samples, our model can generalize the recognition of merchants, amounts, and other fields from English to Arabic.
  arXiv  Detail & Related papers  (2023-07-16T00:45:42Z)
• HuBERT-TR: Reviving Turkish Automatic Speech Recognition with Self-supervised Speech Representation Learning [10.378738776547815]
  We present HuBERT-TR, a speech representation model for Turkish based on HuBERT. HuBERT-TR achieves state-of-the-art results on several Turkish ASR datasets.
  arXiv  Detail & Related papers  (2022-10-13T19:46:39Z)
• Towards Efficient NLP: A Standard Evaluation and A Strong Baseline [55.29756535335831]
  This work presents ELUE (Efficient Language Understanding Evaluation), a standard evaluation, and a public leaderboard for efficient NLP models. Along with the benchmark, we also pre-train and release a strong baseline, ElasticBERT, whose elasticity is both static and dynamic.
  arXiv  Detail & Related papers  (2021-10-13T21:17:15Z)
• FBERT: A Neural Transformer for Identifying Offensive Content [67.12838911384024]
  fBERT is a BERT model retrained on SOLID, the largest English offensive language identification corpus available with over $1.4$ million offensive instances. We evaluate fBERT's performance on identifying offensive content on multiple English datasets and we test several thresholds for selecting instances from SOLID. The fBERT model will be made freely available to the community.
  arXiv  Detail & Related papers  (2021-09-10T19:19:26Z)
• InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective [84.78604733927887]
  Large-scale language models such as BERT have achieved state-of-the-art performance across a wide range of NLP tasks. Recent studies show that such BERT-based models are vulnerable facing the threats of textual adversarial attacks. We propose InfoBERT, a novel learning framework for robust fine-tuning of pre-trained language models.
  arXiv  Detail & Related papers  (2020-10-05T20:49:26Z)
• GREEK-BERT: The Greeks visiting Sesame Street [25.406207104603027]
  Transformer-based language models, such as BERT, have achieved state-of-the-art performance in several downstream natural language processing tasks. We present GREEK-BERT, a monolingual BERT-based language model for modern Greek.
  arXiv  Detail & Related papers  (2020-08-27T09:36:14Z)
• ConvBERT: Improving BERT with Span-based Dynamic Convolution [144.25748617961082]
  BERT heavily relies on the global self-attention block and thus suffers large memory footprint and computation cost. We propose a novel span-based dynamic convolution to replace these self-attention heads to directly model local dependencies. The novel convolution heads, together with the rest self-attention heads, form a new mixed attention block that is more efficient at both global and local context learning.
  arXiv  Detail & Related papers  (2020-08-06T07:43:19Z)
• ParsBERT: Transformer-based Model for Persian Language Understanding [0.7646713951724012]
  This paper proposes a monolingual BERT for the Persian language (ParsBERT) It shows its state-of-the-art performance compared to other architectures and multilingual models. ParsBERT obtains higher scores in all datasets, including existing ones as well as composed ones.
  arXiv  Detail & Related papers  (2020-05-26T05:05:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.