SemiAdapt and SemiLoRA: Efficient Domain Adaptation for Transformer-based Low-Resource Language Translation with a Case Study on Irish
This work addresses the barrier to entry for researchers working on low-resource languages like Irish by making domain adaptation more efficient and accessible.
The paper tackled the problem of computationally expensive fine-tuning for low-resource language translation by introducing SemiAdapt and SemiLoRA, which outperformed full-domain fine-tuning and matched or exceeded full-model fine-tuning in neural machine translation, with models released as open resources for Irish translation.
Fine-tuning is widely used to tailor large language models for specific tasks such as neural machine translation (NMT). However, leveraging transfer learning is computationally expensive when fine-tuning large multilingual models with billions of parameters, thus creating a barrier to entry for researchers working on low-resource domains such as Irish translation. Parameter-efficient fine-tuning (PEFT) bridges this gap by training on a fraction of the original model parameters, with the Low-Rank Adaptation (LoRA) approach introducing small, trainable adapter layers. We introduce SemiAdapt and SemiLoRA as semi-supervised inference-efficient approaches that strengthen domain adaptation and lead to improved overall performance in NMT. We demonstrate that SemiAdapt can outperform full-domain fine-tuning, while most notably, SemiLoRA can propel PEFT methods to match or even outperform full-model fine-tuning. We further evaluate domain-by-dataset fine-tuning and demonstrate that our embedding-based inference methods perform especially well on larger and noisier corpora. All Irish translation models developed in this work are released as open resources. These methods aim to make high-quality domain adaptation and fine-tuning more accessible to researchers working with low-resource languages.