1Cademy - Greedy Search Strategy in Sequence-to-Sequence Models

Learn Before

Greedy Search (Greedy Decoding)

Concept

Greedy Search Strategy in Sequence-to-Sequence Models

In sequence-to-sequence models, the greedy search strategy is a straightforward decoding method where, at any time step t', the model selects the single token from the vocabulary \mathcal{Y} that has the highest conditional probability. This is mathematically expressed as: y_{t'} = \operatorname*{argmax}{y \in \mathcal{Y}} P(y \mid y_1, \ldots, y{t'-1}, \mathbf{c}) where \mathbf{c} is the context vector representing the source input. The generation of the output sequence concludes once the model outputs the end-of-sequence token ("") or reaches a predefined maximum length T'.