Chapter 14
Sequence-to-Sequence Networks and Natural Language Translation
In Chapter 11, “Text Autocompletion with LSTM and Beam Search,” we discussed many-to-many sequence prediction problems and showed with a programming example how it can be used for autocompletion of text. Another important sequence prediction problem is to translate text from one natural language to another. In such a setting, the input sequence is a sentence in the source language, and the predicted output sequence is the corresponding sentence in the destination language. It is not necessarily the case that the sentences consist of the same number of words in the two different languages. A good English translation of the French sentence Je suis étudiant is “I am a student,” ...
Get Learning Deep Learning: Theory and Practice of Neural Networks, Computer Vision, NLP, and Transformers using TensorFlow 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.
