PDF File
PPT File
Image
Upload PDF
MinerU document parsing & SelectTranslate
MinerU is a powerful document parsing tool developed by OpenDataLab, a subsidiary of the Shanghai Artificial Intelligence Laboratory. It was born in the pre-training process of the Intern large language model. It focuses on solving the challenges of symbol conversion and content understanding in complex documents such as scientific literature and professional reports. It has surpassed 48K stars on GitHub and is free to use.
SelectTranslate is deeply integrated with MinerU, providing users with a high-quality document translation experience.
SelectTranslate is deeply integrated with MinerU, providing users with a high-quality document translation experience.
The difference between PDF Plus and Ordinary PDF Translation
PDF Plus Translation | Ordinary PDF Translation | |
|---|---|---|
| Document parsing technology | Multi-modal AI + OCR intelligent parsing | Local JavaScript parsing algorithm |
| Complex formula recognition | ||
| Chemical molecule and reaction formula recognition | ||
| Scanned document translation (image recognition) | ||
| Table Recognition / Table Rotation | ||
| Double column, three column layout conversion | ||
| Side-by-Side Review | ||
| Export PDF |
Bilingual Comparison & Side-by-Side Review
Seamlessly integrate online document browsing with intelligent translation. Clicking on the original paragraph will quickly locate the corresponding translation, and clicking on the translation will also link back to find the original paragraph, helping you to conveniently compare and learn efficiently, and improving the efficiency of cross-language reading and content verification.
Complex Element Extraction
Based on multi-modal intelligent parsing technology, accurately extract complex elements such as text, mathematical formulas, images, tables, molecular structures, chemical reaction formulas, and handwritten content. Keep formulas and charts intact, intelligently translate text content, and easily cope with the translation of various professional academic documents!
Scanned Document Translation
Combining OCR optical character recognition with multi-modal intelligent parsing technology, accurately identify and extract content from scanned documents, enabling high-quality translation of scanned documents.
Export translated content
Export as HTML
The translated content can be exported and saved in HTML format, making it easy to read in browsers on different devices.
Export as PDF
You can export and save the translated content in PDF format, preserving the original layout and style as seen in the online translation reading.