Translation Tools Can Save Less Popular Languages
With some languages about to disappear, Microsoft and Google are working hard to keep them alive with a new translation technology that aims at languages that are left behind by the Web. Though both of the web giants have been working on developing translation technologies for many years, their focus, till now, is on such most spoken languages in the international trade like English, Chinese, and Spanish.
The current translation tools developed by Microsoft and Google, which are offered free of charge, are a great success of the big data. It is not learning as a human translator would do, with studying the rules and grammar of different target languages, a translation tool’s algorithms can learn the most efficient ways to translate one language into another by statistically making comparisons with millions of online translations that have been done previously by the human translators.
Both companies have shifted from that formula a little to revive less used languages. It is noted that Google could recently launch experimental “alpha” support for a group of five Indian languages (Telugu, Bengali, Gujarati, Kannada, and Tamil) by offering its software some direct instructions in grammar and structure rules. At the same time, Microsoft has released a service that allows a specific community to set up a translation system for its own language by providing its own source language materials.
Kristin Tolle, a director at Microsoft Research, said, “Microsoft is also interested in helping languages not in common use online, to prevent those languages from being sidelined and falling from use.” Her team recently have published a website with the aim of helping all people to create their own translation software, called Translation Hub. It targets the communities that want to ensure their language is still alive on the Web.
When using Translation Hub software, it involves setting up an account and then uploading source materials in the two languages to be translated between. Machine learning algorithms for Microsoft make use of those materials and can then try to translate any writing in the new language settings.
“There is a lot of truth to what Microsoft is saying,” says Greg Anderson, director of nonprofit Living Tongues, which documents, does some research on the affairs, and attempts to help disappearing languages. “Today’s playing field involves a digital online presence whether you are community or a company—if you don’t have a Web presence, you don’t exist, on some level.”