Processing Documents from an Unsupported Language or Encoding

If you have a collection of documents from an unsupported language or encoding, you might still be able to successfully process the text and get useful results. Follow these steps:
  1. Set the language to English.
  2. Turn off these parse properties:
    • Stem Terms
    • Different Parts of Speech
    • Noun Groups
    • Find Entities
  3. Run the Text Miner node.
Many of the terms might have characters that do not display correctly, but the Interactive Results window should function and you should be able to create stop lists, start lists, and synonym lists.