TiSpell: A Semi-Masked Methodology for Tibetan Spelling Correction covering Multi-Level Error with Data Augmentation

Multi-level Tibetan spelling correction addresses errors at both the character and syllable levels within a unified model. Existing methods focus mainly on single-level correction and lack effective integration of both levels. Moreover, there are no open-source datasets or augmentation methods tailored for this task in Tibetan. To tackle this, we propose a data augmentation approach using unlabeled text to generate multi-level corruptions, and introduce TiSpell, a semi-masked model capable of correcting both character- and syllable-level errors. Although syllable-level correction is more challenging due to its reliance on global context, our semi-masked strategy simplifies this process. We synthesize nine types of corruptions on clean sentences to create a robust training set. Experiments on both simulated and real-world data demonstrate that TiSpell, trained on our dataset, outperforms baseline models and matches the performance of state-of-the-art approaches, confirming its effectiveness.

@article{liu2025_2505.08037,
  title={ TiSpell: A Semi-Masked Methodology for Tibetan Spelling Correction covering Multi-Level Error with Data Augmentation },
  author={ Yutong Liu and Feng Xiao and Ziyue Zhang and Yongbin Yu and Cheng Huang and Fan Gao and Xiangxiang Wang and Ma-bao Ban and Manping Fan and Thupten Tsering and Cheng Huang and Gadeng Luosang and Renzeng Duojie and Nyima Tashi },
  journal={arXiv preprint arXiv:2505.08037},
  year={ 2025 }
}