Data-Driven Approach for Formality-Sensitive Machine Translation: Language-Specific Handling and Synthetic Data Generation

Abstract: In this paper, we introduce a data-driven approach for Formality-Sensitive Machine Translation (FSMT) that caters to the unique linguistic properties of four target languages. Our methodology centers on two core strategies: 1) language-specific data handling, and 2) synthetic data generation using large-scale LLMs and empirical prompt engineering. This approach demonstrates a considerable improvement over the baseline, highlighting the effectiveness of data-centric techniques. Our prompt engineering strategy further improves performance by producing superior synthetic translation examples.