Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation
This addresses machine translation challenges in low-resource scenarios, offering a method to enhance translation quality when data is limited, though it is incremental as it builds on existing LLM in-context learning techniques.
The paper tackles the problem of low-resource machine translation by proposing compositional translation, a novel LLM-based approach that decomposes sentences into phrases for easier translation, resulting in improved performance on benchmarks like FLORES 200, NTREX 128, and TICO-19.
The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. Machine Translation (MT) has been shown to benefit from in-context examples, in particular when they are semantically similar to the sentence to translate. In this paper, we propose a new LLM-based translation paradigm, compositional translation, to replace naive few-shot MT with similarity-based demonstrations. An LLM is used to decompose a sentence into simpler phrases, and then to translate each phrase with the help of retrieved demonstrations. Finally, the LLM is prompted to translate the initial sentence with the help of the self-generated phrase-translation pairs. Our intuition is that this approach should improve translation because these shorter phrases should be intrinsically easier to translate and easier to match with relevant examples. This is especially beneficial in low-resource scenarios, and more generally whenever the selection pool is small or out of domain. We show that compositional translation boosts LLM translation performance on a wide range of popular MT benchmarks, including FLORES 200, NTREX 128 and TICO-19. Code and outputs are available at https://github.com/ArmelRandy/compositional-translation