RNNs and LSTMs

14.6 Common RNN architectures

1. Summarize the four common RNN architectures for NLP tasks.
   Sequence labeling (one output per input token, e.g. POS); sequence classification (one output from the end of the sequence, e.g. sentiment); language modeling (predict the next token at each step); encoder-decoder (map an input sequence via a context to an output sequence of different length).
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 14, §14.6, p. 318