Google has added support for the constructed language

Feb 23, 2012 10:31 GMT  ·  By

Google Translate is constantly adding more languages, but new languages tend to be rarer, at least on the internet, than the ones already supported. It's going to be harder and harder to add more languages to the service since there will be less data for the machine translation algorithms to use.

The latest addition, Esperanto, proved rather easy for Google's algorithms to learn, it seems. Esperanto was created more than 100 years ago with the goal of having one common language that all the peoples of the world would be able to speak.

While the planet hasn't yet converted to Esperanto, there are hundreds of thousands of fluent speakers. What's more, the quality of the work in Esperanto found online as well as what Google has been able to gather is quite good.

"The Google Translate team was actually surprised about the high quality of machine translation for Esperanto. As we know from many experiments, more training data (which in our case means more existing translations) tends to yield better translations," Google explained.

"For Esperanto, the number of existing translations is comparatively small. German or Spanish, for example, have more than 100 times the data; other languages on which we focus our research efforts have similar amounts of data as Esperanto but don’t achieve comparable quality yet. Esperanto was constructed such that it is easy to learn for humans, and this seems to help automatic translation as well," it added.

The usual caveats apply, Google translations for Esperanto are by no means perfect, in fact, they should be poorer than for more widely used languages like English.

Still, it's an important addition, not only from an academic point of view, there are millions of people with some knowledge of Esperanto. Google Translate should make practicing and learning the language easier. With the addition of Esperanto, there are now 64 languages supported by Google Translate.