Approaches

Approaches to machine translation


The earliest machine translation systems were built with rule-based approaches.

By the 2010s, the top systems, like Google Translate, used statistical machine translation (SMT). Statistical machine translation is also known as phrase-based machine translation (PBMT).

By the 2020s, the top systems used neural machine translation. A few of the neural systems launched an adaptive customisation feature.

Each paradigm shift made machine translation systems more accurate and also easier to build. The result was more language support and more production systems from more companies.


Table of contents


Want to learn more about Approaches?


Edit this article →

Machine Translate is created and edited by contributors like you!

Learn more about contributing →

Licensed under CC-BY-SA-4.0.

Cite this article →