In structured prediction and NLP, decoding refers to predicting the output given the input. For example, the input could be a sentence, and the output could be a sequence of part-of-speech tags. In this case, decoding is predicting the POS tags given the input sentence. The decoding algorithm is the algorithm used to make the predictions (such as dynamic programming, beam search, integer linear programming, etc). Decoding is also known as inference (see note below).

In NLP and graphical models, inference means making predictions (predicting the output $Y$ given the input $X$), and is another term for decoding. In statistics however, inference means learning (i.e. predicting the parameters of the distribution).

• MAP inference in graphical models
• Dynamic Programming
• Weighted Logic Programming
• Integer Linear Programming

• Beam Search
• Structured Prediction
• Graphical Models
• Integer Linear Programming
• Sequence-to-Sequence Models - Decoding Strategies
• Weighted Logic Programming