Bringing the grand total to 345 languages

Oct 16, 2009 10:04 GMT  ·  By

Google won't stop until its technology can translate between all of the languages on Earth and the company has now made a huge step forward with the addition of 285 new languages to the Google Translator Toolkit, a tool designed for professional translators and based on the Google Translate technology. This brings the total number up to 345 languages available and there are new 10,664 possible translation pairs.

“At Google, we're focusing on how Translator Toolkit can help preserve and revitalize small and minority languages. Minority languages, also called regional, indigenous, heritage or threatened languages, are languages spoken by the minority people in one locale in a sovereign state or country. Were these endangered languages to become extinct, it would mean an immeasurable loss of knowledge, culture and way of life to minority people worldwide,” Michael Galvez, product manager, and Sanjay Bhansali, engineering manager, wrote.

The Google Translator Toolkit itself is now available in 35 languages giving more people a chance to use it. While Google's translation technology is far from perfect, Google Translate is available in 70 established languages offering a reasonable quality translation. However, Google decided to introduce the additional languages to the Translator Toolkit first as the support for them is likely to be spotty at the time and partly because those using the tool are more likely to need all of these new languages.

The translation technology Google employs is based on learning from existing translations, meaning that the more documents it can process the better it will become. This works fine for languages with a great number of documents available with their translation but as the language becomes less used the likelihood of finding documents like these decreases. This is where the Translation Toolkit comes is.

On the one hand it is a useful tool for those doing translations; on the other hand it provides Google with copies of documents translated by human professionals in both their original language as well as the translated one. This is one of the most valuable resources for the translation effort and it is especially crucial for languages spoken by very few people like the ones introduced now.