EasyDeepLearn

How does a bidirectional RNN work and when is it appropriate?

easy

Answer

  • Run two RNNs — one left-to-right, one right-to-left — and concatenate their hidden states at each timestep.
  • Provides access to both past and future context.
  • Appropriate for tagging tasks (POS, NER), speech recognition, classification.
  • Not usable for online generation (you need the full sequence).
  • Transformers with full attention subsume this by attending both directions in encoder-only setups (BERT).
Check yourself — multiple choice
  • Only one direction
  • Two RNNs (fwd + bwd) with concatenated hidden states — for tagging/classification, not for generation
  • BiRNNs are always causal
  • Same as attention

BiRNN: forward + backward RNNs concatenated → past + future context.

#rnn

Practise Deep Learning

214 interview questions in this topic.

Related questions