If you have an interest in an area you normally find that academic books cover the subject in exacting detail and provide lots of references so that you can easily extend your knowledge. This book falls into that area. It starts by introducing Natural Language Processing (NLP), then it introduces Prolog (a logic programming language) and then pulls everything together by combining NLP and Prolog.

Being a declarative language (rather than a procedural language such as C++) you simply state your requirements as a number of facts and then Prolog tries to prove new facts (and ultimately your goal) by inferring new facts.

This is an ideal method of processing for NLP and can lead to small and elegant programs. On the downside you need to have a firm understanding of recursion in order to get the most from the language. Writing a small Prolog program without recursion is not possible for any useful problem. You also need to be able to visualise the way in which your program executes, since defining your facts in a different order can lead to much more efficient programs. This book tackles these areas.

NLP programming is considered a branch of AI and the book contains references to the main AI literature and being a recent book it is up to date with the latest research developments. I would have no hesitation in recommending this book for anybody with an interest (passing or otherwise) in this subject.