Relay Decoding: Concatenating Large Language Models for Machine Translation
This addresses a cost-effective solution for machine translation in low-resource language pairs, though it is incremental as it builds on existing model concatenation ideas.
The paper tackles the challenge of using large language models for machine translation when no single model supports both source and target languages, proposing Relay Decoding to concatenate two models with a mapping layer, achieving superior results on Multi30k and WikiMatrix datasets.
Leveraging large language models for machine translation has demonstrated promising results. However, it does require the large language models to possess the capability of handling both the source and target languages in machine translation. When it is challenging to find large models that support the desired languages, resorting to continuous learning methods becomes a costly endeavor. To mitigate these expenses, we propose an innovative approach called RD (Relay Decoding), which entails concatenating two distinct large models that individually support the source and target languages. By incorporating a simple mapping layer to facilitate the connection between these two models and utilizing a limited amount of parallel data for training, we successfully achieve superior results in the machine translation task. Experimental results conducted on the Multi30k and WikiMatrix datasets validate the effectiveness of our proposed method.