As I said in class, I am not going to expect memorization of formulas
or algorithms. The ideas are more important than the memorization of
things you could look up, so if you need a definition, formula, or
algorithm, I'll give it to you. However, I'll expect you to
*understand* the formulas, definitions, and algorithms covered
in the readings, with a higher emphasis on things we discussed in
class. Also, I will not totally blindside you with lots of questions
from the readings that are completely unrelated to what we covered in
class, to test whether or not you did/studied the readings. On the
other hand, if you study only what we discussed in class, ignoring
everything else in the readings, I can't promise you won't get bitten
on some question.

Again, especially on algorithms, but also with issues in general, the understanding is what's important. Knowing how to walk through algorithms we discussed: good. Being able to demonstrate you understand the ideas behind algorithms rather than just doing it by rote, e.g. pros and cons: better. Understanding an algorithm well enough to modify it for some purpose: even better.

That said, here are some specific things you can safely ignore in your studying. (Section numbers from Manning and Schuetze.)

- 2.1.9 Don't need to know (DNTK) standard distributions
- 3.3 DNTK semantics stuff -- to be covered in 2nd half of semester5.3
- 5.3 DNTK specific tests, just the ideas behind hypothesis testing and significance.
- 6.3.2 DNTK backing off
- 6.3.4 DNTK other smoothing methods
- 9.4 DNTK implementation, etc.
- 10.2.3 DNTK POS tagger variations
- 10.3.2 DNTK HMM initialization issues
- 10.4 DNTK transformation-based learning
- 10.5 DNTK other methods, languagese
- 10.6 DNTK applications of tagging
- 11.3.4 DNTK PCFG unsupervised training (Inside-Outside definitions, yes; *algorithm*, no)
- 11.4 DNTK Inside-Outside algorithm problems
- 12.1.6 DNTK left-corner parsing

I hope that this provides you with some useful guidance. My goal is to write an exam that is interesting (to you), informative (to me), and fair (to all).