Peter Norvig review of "Foundations of Statistical NLP"

[robdoherty2]

There are lots of books (and even more junk email) with titles like "Get Rich Quick". On the surface, this book is the exact opposite: a scholarly, scientific text aimed at comprehensive, accurate description, not at commercial hype. But if someone told me I had to make a million bucks in one year, and I could only refer to one book to do it, I'd grab a copy of this book and start a web text-processing company. Your return on investment might not be $1M, but this book delivers everything it promises. For all the major practical applications of statistical text processing, this book accurately and clearly surveys the major techniques. It often has pretty good advice about which techniques to prefer, but sometimes reads more like a catalog of listings (this reflects not on the authors' failing, but rather on the field's immaturity). It's worth comparing this book to the other recent NLP text: Jurafsky and Martin's. (Disclaimer: I worked with them on the preparation of their text.) Jurafsky and Martin cover much more ground, including many aspects that are ignored by Manning and Schutze. So if you want a general overview of natural language, if you want to know about the syntax of English, or the intricacies of dialog, then Jurafsky and Martin is for you. But if your needs are more focused on the algorithms for lower-level text processing with statistical techniques, then Manning and Schutze is far more comprehensive. If you're a serious student or professional in NLP, you just have to have both.

[cbo]

I'm really not sure why this was posted without the link. Maybe it was just an accident.

Here's the link to his review, though it's now over 10 years old:

http://www.amazon.com/review/R3GSYXSKRU8V17

He has several reviews and booklists on Amazon, both of which I've found to be infinitely helpful.

[TheCowboy]

For anyone who has read this book, any thoughts on if this book has aged well? Is there a better book out? Anything more relevant to the current state of the art?

[robdoherty2 → TheCowboy]

I've read the book, although it would be more accurate to say that I skimmed it since it was a bit over my head when I got it a year or so ago.

I am going through it again now that I've brushed up a bit on some of the math, and in anticipation of the upcoming Stanford course on NLP (http://www.nlp-class.org/), which is being taught by one of the authors.

I think that the material is still fairly relevant, especially in that it is a 'foundation' of Statistical NLP, and especially for someone relatively new to the material (like me). That said, if you take a look at the link to the course, the professors recommend a few different texts:

"The best textbook for the class is Jurafsky and Martin, Speech and Language Processing 2nd Edition (http://www.cs.colorado.edu/~martin/slp.html), complemented by chapters from Manning, Schütze and Raghavan 2008 (http://nlp.stanford.edu/IR-book/); other useful, good books include Manning and Schütze 1999, and Bird, Klein and Loper 2009."

I'd be interested to hear others thoughts on this as well.