Minority languages also make it to Google’s Statistical MT

by Manuel Herranz

Google has just added five new languages to its machine translation platform: Azerbaijani, Armenian, Basque, Urdu and Georgian. You can find the five of them on Google Translate. These new languages bringing the total number of languages on Google Translate to 57.

These languages are still in alpha status, though. The translations maybe less fluent than other languages as Google has gathered less data to feed its statistical machine translation system, but they should still help you understand the multilingual web. “Good working languages” are those for which Google could find a lot of bilingual, aligned data. These included initially the 6 languages of the United Nations (English, French, Spanish, Chinese and Russian) because the UN had released large sets of parallel corpora which contained sentences aligned from one language to another. Google also used parallel corpora from the European Union and other institutions which had released large amounts of data.

You can help Google Translate improve translation quality as well. If you notice an incorrect translation, you can click “Contribute a better translation” to correct it. If you are a translator, then you can contribute translation memories with the Translator Toolkit. This will help Google build better machine translation systems especially for languages that are not well represented on the web.

There are currently about 100 million people who speak Armenian, Azerbaijani, Basque, Georgian and Urdu. With these new updates, these people can now more easily access the entire multilingual web in their own language.

The service limits the number of paragraphs, or range of technical terms, that will be translated. It is also possible to enter searches in a source language that are first translated to a destination language allowing you to browse and interpret results from the selected destination language in the source language. For some languages, users are asked for alternate translations such as for technical terms, to be included for future updates to the translation process. Text in a foreign language can be typed, and if “Detect Language” is selected, it will not only detect the language, but it will translate into English by default.

If the user is translating English to French, for example, and the language needs to be swapped into reverse order (French to English), clicking “swap” will reverse the orientation of the language translation.

Next time you think languages, think Pangeanic
Your Machine Translation Customization Solutions

   

Leave a Reply

Your email address will not be published. Required fields are marked *


4 × two =

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>