Graham Tritt   •   over 2 years ago

Conversion of a book into a rich text version

I'd like an app which can read a book and create a word frequency list. Then this should reduce the words to "headwords" by eliminating derivations (.-ing, -er, -s, -ist, etc). I'm thinking of the English language. This list (preferably with context information) should be correlated against the English Vocabulary Profile (relating words to CEFR levels of difficulty) and to text corpuses and national databases. The book could be converted into a version in which words or phrases are linked to meanings or translations. Such a "rich text" version would be customized to reader ability level.