I think the book "Speech and Language Processing, 2nd Edition" from Prof. Daniel Jurafsky is very good http://www.amazon.com/Speech-Language-Processing-Daniel-Jura...

You can also check out the great online NLP course taught by the author and Prof. Chris Manning from Stanford: https://www.youtube.com/watch?v=nfoudtpBV68&list=PL6397E4B26...

Stanford's NLP (Natural Language Processing = Computational Linguistics) course (taught by Chris Manning, one of the best known names in the field) is online, with both videos and transcripts available[1]. The standard intro textbook to the field is Jurafsky and Martin[2], which is an excellent read if you're at all interested in NLP/CompLing.

1: http://see.stanford.edu/see/lecturelist.aspx?coll=63480b48-8...

2: http://www.amazon.com/Speech-Language-Processing-Daniel-Jura...

What you are trying to do is very hard. Statistical NLP is the way to go for unbounded domains. You might be able to do better semantic analysis for smaller closed domains.

There is a relatively new great book on NLP out now that I suggest you take a look at. Particularly the chapters semantics are very useful, but they should give you an idea of how incredibly difficult what you're trying to do is.

Book: http://www.amazon.com/Language-Processing-Prentice-Artificia...