Introduction: Sequence-to-Sequence Learning—NMT

Get an overview of sequence-to-sequence learning and its application in machine translation.

Sequence-to-sequence learning

Sequence-to-sequence learning is the term used for tasks that require mapping an arbitrary-length sequence to another arbitrary-length sequence. This is one of the most sophisticated tasks in NLP, which involves learning many-to-many mappings. Examples of this task include neural machine translation (NMT) and creating chatbots. NMT is where we translate a sentence from one language (source language) to another (target language). Google Translate is an example of an NMT system. Chatbots (that is, software that can communicate with and answer a person) are able to converse with humans in a realistic manner. This is especially useful for various service providers because chatbots can be used to find answers to easily solvable questions that customers might have instead of redirecting them to human operators.

Statistical machine translation

In this chapter, we’ll learn how to implement an NMT system. However, before diving directly into such recent advances, we’ll first briefly visit some statistical machine translation (SMT) methods, which preceded NMT and were the state-of-the-art systems until NMT caught up. Next, we’ll walk through the steps required for building an NMT. Finally, we’ll learn step by step how to implement a real NMT system that translates from German to English.

Get hands-on with 1200+ tech skills courses.