I am pre-processing some texts and I wonder what the best practice is when preparing your texts for word alignment. I don't know how aligners such as fast align and GIZA++ work under the hood, but I could assume that they take capital letters as distinguished characters. Is there, therefore, any reason to lower case your text in such a situation? Is this language dependent? It might, for instance, be interesting for a language with many capital letters, such as German, to do so or not.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.