Why is it important to gather and analyze data about the languages in scope?

The main reason is that all taxonomy fields should have their names translated into all the languages presented in the documents to be processed.

Different Document Understanding components have support for different languages, so they have to be selected according to the requirements.

This is a standard check but has no actual effect on the Document Understanding process.

If an ML (Machine Learning) extractor is used, the model schema fields should be renamed according to the most frequently used language from the documents to be processed