You’ve tried various RNN models till now. Finally, let’s build one more model – a bidirectional LSTM and compare its performance in terms of accuracy and training time as compare to the previous models.
The bidirectional LSTM did increase substantially (considering that the accuracy was already hitting the roof). This shows the power of bidirectional LSTMs. However, this increased accuracy comes at a cost. The time taken was almost double than a normal LSTM network.
This brings us to the end of the POS tagging demonstration. In the next segments, you’ll do some fun experiments and learn how to generate text using RNNs.
Report an error