Bidirectional Recurrent Neural Networks

Editorial record

Plain-language summary

The architecture processes a sequence left-to-right with one recurrent network and right-to-left with a second, then merges the two hidden states at each position before making a prediction. This gives every output access to the entire input sequence rather than only the elements seen so far. Because it requires the whole sequence up front it suits offline labeling tasks like speech and text tagging, and the bidirectional design later combined with LSTMs to become a standard component for sequence labeling.