Can I read Data-Driven Approach for Formality-Sensitive Machine Translation: Language-Specific Handling and Synthetic Data Generation on EtoBox?

Data-Driven Approach for Formality-Sensitive Machine Translation: Language-Specific Handling and Synthetic Data Generation by Lee, Seugnjun; Moon, Hyeonseok; Park, Chanjun; Lim, Heuiseok is a scholarly article available to read on EtoBox.

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

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 language models 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.

Author

Lee, Seugnjun; Moon, Hyeonseok; Park, Chanjun; Lim, Heuiseok

Published

2023

Language

EN