11 Sequence-to-sequence learning: Part 1

This chapter covers

  • Understanding sequence-to-sequence data
  • Building a sequence-to-sequence machine translation model
  • Training and evaluating sequence-to-sequence models
  • Repurposing the trained model to generate translations for unseen text

In the previous chapter, we discussed solving an NLP task known as language modeling with deep recurrent neural networks. In this chapter, we are going to further our discussion and learn how we can use recurrent neural networks to solve more complex tasks. We will learn about a variety of tasks in which an arbitrary-length input sequence is mapped to another arbitrary-length sequence. Machine translation is a very appropriate example of this that involves converting ...

Get TensorFlow in Action now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.