Problems analysing (non-english) archeological texts.

  • Many documents are in other languages than english, whereas much of the extant AI software is written and optimized for the english language.

  • The format of published or scanned texts is often difficult to translate into the plain ASCII that is preferred for most text analysis applications.

    • This is especially true when processing files in Microsoft Word format on other platforms.
      What is written in Microsoft Word may be lost outside a Microsoft environment or when Microsoft changes its formats.

    • Better to write and store your documents in an Open format from the start.