by Globalization Partners International
The modern history of automated translation begins primarily in the post WW2 & Cold War era, when the race for information and technology motivated researchers and scholars to find a way to quickly translate information.
In the past when we had to figure out the meaning of a word from another language, we made use of a dictionary. Not only was this a very time consuming task but it was kind of irritating owing to the fact that it was difficult to interpret the meanings. Moreover, when an entire paragraph or note had to be translated, this could be very difficult because one word had several meanings. So what to do? That’s where the machine translator came into the picture.
While typing a message, the computer you’re working on identifies the language you use instantly. As part of his PhD project, Binyam Gebrekidan Gebre trained a computer program to perform the same trick on sign languages. Language recognition is the first step for automatic translations of videos.
To study sign languages – natural languages that use hands, facial and body movements to convey meaning – large data collections are needed. Transcription of videos is very time consuming though and therefore very expensive. The Max Planck Institute for Psycholinguistics in Nijmegen set up a project to automate sign language transcription.
Back in November 2014, Skype launched a preview of Skype Translator, which will aim to provide real-time translation of conversations in over 40 languages. Hot on its heels, Google has now updated its own app to include an instant interpreting function using voice recognition, as well as an impressive translation feature which utilises a phone’s camera to automatically translate text viewed through the lens.
Long gone are the days of trying to decipher the unusual looking dishes on foreign menus – now all you have to do is hover your phone above the page and receive an instant translation. Here at Web-Translations, we’ve given the app a quick road test using three major tourist preoccupations: warning signs, tourist information and those all important menus. Take a look at how we got on below.
Researchers at the University of Amsterdam are using neural networks to help statistical machine translation systems learn what all human translators know—that the best translation of a word often depends on the context.
The neural network is able to derive grammatical functions of words without having explicit knowledge of the grammar, said Ke Tran, one of the researchers. This means that to learn word functions the method does not depend on examples hand-picked by the researchers, which can be a difficult and costly process, especially for languages with few speakers.
Read more: http://tinyurl.com/oejeyyh
This is the new home of Dirty Little Secrets for Translators, our wordpress blog.
