Abstract
Machine Translation (MT) has advanced from rule-based and statistical methods to neural approaches based on the Transformer architecture. While these methods have achieved impressive results for high-resource languages, low-resource varieties such as Sylheti remain underexplored. In this work, we investigate Bengali-to-Sylheti translation by fine-tuning multilingual Transformer models and comparing them with zero-shot large language models (LLMs). Experimental results demonstrate that fine-tuned models significantly outperform LLMs, with mBART-50 achieving the highest translation adequacy and MarianMT showing the strongest character-level fidelity. These findings highlight the importance of task-specific adaptation for underrepresented languages and contribute to ongoing efforts toward inclusive language technologies.
Abstract (translated)
机器翻译（MT）已经从基于规则和统计的方法发展到以Transformer架构为基础的神经方法。尽管这些方法在高资源语言上取得了令人印象深刻的结果，但低资源语言如锡莱蒂语的研究仍然较少。在这项工作中，我们通过微调多语言Transformer模型并将其与零样本大型语言模型（LLMs）进行比较来研究孟加拉语到锡莱蒂语的翻译。实验结果表明，经过微调的模型显著优于LLM，在翻译充分性方面，mBART-50表现最佳；在字符级别保真度方面，MarianMT表现出最强的能力。这些发现强调了为未被充分代表的语言进行任务特定适应的重要性，并为包容性语言技术的发展做出了贡献。
URL
https://arxiv.org/abs/2510.18898
