Many NLP tasks have at their core a subtask of extracting the dependencies-who did what to whom-from natural language sentences. This task can be understood as the inverse of the problem solved in different ways by diverse human languages, namely, how to indicate the relationship between different parts of a sentence. Understanding how languages solve the problem can be extremely useful in both feature design and error analysis in the application of machine learning to NLP. Likewise, understanding cross-linguistic variation can be important for the design of MT systems and other multilingual applications. The purpose of this book is to present in a succinct and accessible fashion information about the morphological and syntactic structure of human languages that can be useful in creating more linguistically sophisticated, more language-independent, and thus more successful NLP systems. Table of Acknowledgments / Introduction/motivation / Introduction / Morphophonology / Morphosyntax / Introduction / Parts of speech / Heads, arguments, and adjuncts / Argument types and grammatical functions / Mismatches between syntactic position and semantic roles / Resources / Bibliography / Author's Biography / General Index / Index of Languages
The biggest problem is that the book reads like a study guide, with only mere bullets of important or pertinent information to support or elucidate upon the bullets. Furthermore, the book fails to really discuss how any of these issues may be handled in NLP other than to say things like "this may present problems for NLP systems."
Another problem that presents itself is that there are so many terms that are thrown out without properly defining or explaining them. As someone from a linguistics background, I was familiar with most of the information and terms used, but the issue is that this book is written to introduce people from a CS background to linguistics. In that regard, I think it fails, as I believe it would require extensive external searching to fully understand terminology, examples, and points made, especially since many of the tables and examples included have very minimal explanation.
It contains several example from a linguistic perspective of morphology, phonology, syntax, semantic that are practical for having a broader perspective of the role it plays linguistic technique and how the link together with NLP applications.
BTW this book was a gateway for me to read other interesting material from Steven Pinker, specifically The language instict.
The title is quite misleading, since it doesn't really deal that much with computational linguistics or NLP; anyway it serves as a good (but not perfect) introduction to some questions in (theoretical) linguistics..
A comprehensive introduction to linguistics. It works better as a reference, such as when you're doing some research and get stuck on a concept, rather than a book I'd read in my free time.