Chapter 19 sections from Deep Learning with PyTorch.
5 items
A sequence-to-sequence model maps one sequence to another sequence.
Teacher forcing is a training method for autoregressive sequence models. It is used when a model generates an output sequence one token at a time, but during training we already know the correct output sequence.
Beam search is a decoding algorithm for autoregressive sequence models. It is used when a model must generate a sequence, but greedy decoding is too narrow.
Neural machine translation maps a sentence in one language to a sentence in another language using a neural sequence model. The model receives a source sentence and generates a target sentence.
Speech recognition maps an acoustic signal to a text sequence. The input is continuous audio. The output is discrete symbols: characters, subword tokens, words, or phonemes.