Marco, Thanks a lot for the detailed answer. This is really helpful!
Thank you Arnoud for the quick reply. These functions seem useful indeed.
These are probably useful functions for you:
http://reference.wolfram.com/language/ref/TextStructure.html
TextStructure["The boy in white is playing with the nice girl"]
http://reference.wolfram.com/language/ref/ExampleData.html
ExampleData[{"Text","DeclarationOfIndependence"}]
http://reference.wolfram.com/language/ref/TextSentences.html
TextSentences["This is a sentence. This is another sentence."]
