Skip to Main Content U.S. Department of Energy
IN-SPIRE™ Visual Document Analysis

FAQ: What if I have some text that isn't in English?

IN-SPIRE™ visualizations are language-independent, although the use of system or custom stopwords is recommended for optimal visualizations. For some languages such as Chinese, pre-processing with a segmentation tool may be necessary. . If your data contains multiple languages, the documents from one language use very different terms than documents from another, and you will find that the visualizations naturally show the divisions.

If the documents are in a language you cannot read, IN-SPIRE™ does support some third-party language detection and machine-translation software. Queries from your native language can be translated into the language used in the documents, and the Galaxy and ThemeView™ labels, and documents titles and text are translated on demand.

Return to the FAQ page