In general there seems to be no emerging unified theory of NLP to emerge, and most textbooks and courses explain NLP as

collection of problems, techniques, ideas, frameworks, etc. that really are not tied together in any reasonable way other than the fact that they have to do with NLP.

-- Hal Daume

But there are recipes that reoccur frequently, such as Structured Prediction

• Given given some input structure $\x \in \Xs$, such as a word, sentence, or document,
• Predict an output structure $\y \in \Ys$, such as a class label, a sentence or syntactic tree.

the recipe goes as follows:

• Define a parametrized model $s_\params(\x,\y)$ that measures the match of a given $\x$ and $\y$.
• Learn the parameters $\params$ from the training data $\train$ (a continuous optimization problem).
• Given an input $\x$ find the highest-scoring output structure $$\y^* = \argmax_{\y\in\Ys} s(\x,\y)$$ (a discrete optimization problem).

Good NLPers combine three skills in accordance with this recipe:

• modelling,
• continuous optimization and
• discrete optimization.

In this Book

The structured prediction recipe can be found in several places within this book:

• Word-Based MT
• more to come.