Los bericht bekijken
Oud 2 september 2017, 23:15   #3
Nr.10
Secretaris-Generaal VN
 
Nr.10's schermafbeelding
 
Geregistreerd: 26 september 2003
Locatie: van Lissabon tot Vladivostok
Berichten: 31.125
Standaard Technologie om teksten online te vertalen

Einde 2007 begon een voormalig werknemer van Google, de Duitser Gereon Frahling, Linguee.
http://www.linguee.nl/?from=com
In augustus 2017 kondigde Linguee DeepL aan.
DeepL: New Supercomputer-Powered Translator Beats Google and Microsoft
29 aug 2017
DeepL beschikt over een supercomputer met een capaciteit van 5,1 PetaFLOPS, in Ijsland.
In the coming months, DeepL plans to release an API, making its translations available to digital assistants and language learning apps.
CEO Gereon Frahling, a former Google Research member started working on a search engine for translations already back in 2007 after leaving Google. Together with his partner Leo Fink they developed crawlers and different machine learning systems for checking translation quality which resulted in the launch of Linguee in 2009.
In 2010 Linguee was expanded to more language combinations and hit a milestone of one million monthly visitors, making it the world´s most widely used dictionary website. Today, Linguee has more than 200 million visitors per month.
Work on DeepL started back in 2014 when Linguee began to add machine learning tools to learn from its huge database of high-quality translations to nurture a new automated translation system. To improve the translation quality the company recruited hundreds of professional lexicographers who check and correct content generated by algorithms.
In 2016 Linguee starts working on a neural network translation system which is the core of the new DeepL translator.
Om te proberen:
https://www.deepl.com/
Artikel TechCrunch:
DeepL schools other online translators with clever machine learning
29 aug 2017
(...) In an email, Frahling told me that the time was ripe: “We have built a neural translation network that incorporates most of the latest developments, to which we added our own ideas.” An enormous database of over a billion translations and queries, plus a method of ground-truthing translations by searching for similar snippets on the web, made for a strong base in the training of the new model. They also put together what they claim is the 23rd most powerful supercomputer in the world, conveniently located in Iceland. Developments published by universities, research agencies, and indeed Linguee’s competitors showed that convolutional neural networks were the way to go, rather than the recurrent neural networks the company had been using previously. Now isn’t really the place to go into the differences between CNNs and RNNs, so it must suffice to say that for accurate translation of long, complex strings of related words, the former is a better bet as long as you can control for its weaknesses. For example, a CNN could roughly be able to be said to tackle one word of the sentence at a time. This becomes a problem when for instance, as commonly happens, a word at the end of the sentence determines how a word at the beginning of the sentence should be formed. It’s wasteful to go through the whole sentence only to find that the first word the network picked is wrong, and then start over with that knowledge, so DeepL and others in the machine learning field apply “attention mechanisms” that monitor for such potential trip-ups and resolve them before the CNN moves on to the next word or phrase. There are other secret techniques in play, of course, and their result is a translation tool that I personally plan to make my new default.
__________________
Doorzoek forum.politics.be (aangepaste zoekmachine)

Laatst gewijzigd door Nr.10 : 2 september 2017 om 23:19.
Nr.10 is nu online   Met citaat antwoorden