This article is a summary of the following research paper from Google, which used an 8-layer LSTM neural network for achieving state-of-the-art results in language translation.
Introduction
- 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.