PARIS - Designers of machine translation tools still mostly rely on dictionaries to make a foreign language understandable. But now there is a new way: numbers.
Facebook, Google and Microsoft as well as Russia's Yandex, China's Baidu and others are constantly seeking to improve their translation tools.Up to 200 languages are currently used on Facebook, said Mr Antoine Bordes, European co-director of fundamental AI research for the social network. Each word becomes a"vector" in a space of several hundred dimensions. Words that have close associations in the spoken language also find themselves close to each other in this vector space.
These language maps can then be linked to one another using algorithms - at first roughly, but eventually becoming more refined, until entire phrases can be matched without too many errors.For the language pair of English-Romanian, Facebook's current machine translation system is"equal or maybe a bit worse" than the word vector system, said Mr Lample.
Experts at France's CNRS national scientific centre said the approach that Mr Lample has taken for Facebook could produce useful results, even if it does not result in perfect translations. "But the question is what level of performance can be expected" from the word vector method, said Mr Poibeau.
Singapore Latest News, Singapore Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Source: ChannelNewsAsia - 🏆 6. / 66 Read more »
Source: ChannelNewsAsia - 🏆 6. / 66 Read more »
Source: YahooSG - 🏆 3. / 71 Read more »
Source: thenewpaper - 🏆 7. / 63 Read more »
Source: ChannelNewsAsia - 🏆 6. / 66 Read more »
Source: ChannelNewsAsia - 🏆 6. / 66 Read more »