Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles
This work addresses a specific problem in machine translation for researchers and practitioners, offering incremental improvements by focusing on style matching to reduce reliance on few-shot examples.
The paper tackled the performance gap between zero-shot and few-shot machine translation by identifying that matching writing styles can close about 70% of this gap, and explored methods to enhance zero-shot baselines without parallel examples.
Large language models trained primarily in a monolingual setting have demonstrated their ability to generalize to machine translation using zero- and few-shot examples with in-context learning. However, even though zero-shot translations are relatively good, there remains a discernible gap comparing their performance with the few-shot setting. In this paper, we investigate the factors contributing to this gap and find that this gap can largely be closed (for about 70%) by matching the writing styles of the target corpus. Additionally, we explore potential approaches to enhance zero-shot baselines without the need for parallel demonstration examples, providing valuable insights into how these methods contribute to improving translation metrics.