Parameter-efficient fine-tuning (PEFT) methods are increasingly vital in adapting large-scale pre-trained language models for diverse tasks, offering a balance between adaptability and computational efficiency. They are important in Low-Resource Language (LRL) Neural Machine Translation (NMT) to enhance translation accuracy with minimal resources. However, their practical effectiveness varies significantly across different languages. We conducted comprehensive empirical experiments with varying LRL domains and sizes to evaluate the performance of 8 PEFT methods with in total of 15 architectures using the SacreBLEU score. We showed that 6 PEFT architectures outperform the baseline for both in-domain and out-domain tests and the Houlsby+Inversion adapter has the best performance overall, proving the effectiveness of PEFT methods.

参数高效微调方法在适应多样化任务的大规模预训练语言模型中变得越来越重要，通过在资源有限的语言机器翻译中提高翻译准确性来实现适应性和计算效率的平衡。通过使用SacréBLEU评分，我们进行了具备不同资源和域的全面实证实验，评估了共计15种架构的8种参数高效微调方法的性能。结果表明，6种参数高效微调架构在域内和域外测试中均超过了基准线，其中Houlsby+Inversion适配器表现最佳，验证了参数高效微调方法的有效性。

低资源语言翻译的参数高效微调解锁