- The paper proposes a general and end-to-end approach for sequence learning that uses two deep LSTMs, one to map input sequence to vector space and another to map vector to the output sequence.
- For sequence learning, Deep Neural Networks (DNNs) requires the dimensionality of input and output sequences be known and fixed. This limitation is overcome by using the two LSTMs.
Part of course:
Sequence to Sequence Learning with Neural Networks