Xiangyao Ma


2025

pdf bib
PDFMathTranslate: Scientific Document Translation Preserving Layouts
Rongxin Ouyang | Chang Chu | Zhikuang Xin | Xiangyao Ma
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Language barriers in scientific documents hinder the diffusion and development of science and technologies. However, prior efforts in translating such documents largely overlooked the information in layouts. To bridge the gap, we introduce PDFMathTranslate, the world’s first open-source software for translating scientific documents while preserving layouts. Leveraging the most recent advances in large language models and precise layout detection, we contribute to the community with key improvements in precision, flexibility, and efficiency. The work is open-sourced at https://github.com/byaidu/pdfmathtranslate with more than 222k downloads.