News for hackers. Stuff that matters.

A comment on Transitioning entirely to neural machine translation. Parent comment

Re:Transitioning entirely to neural machine translation by dmcy22 on Thursday August 03, 2017 @04:50PM (#14923749)
Impressive indeed. Would you happen to know if Facebook is able to translate without using English as an intermediate language? For example, from Dutch directly to French, without needing to go from Dutch to English to French.
[ Parent | on HN ]
Re:Transitioning entirely to neural machine translation by zlynx on Thursday August 03, 2017 @05:51PM (#14924246)
Reminds me reading about Google's new translator. It apparently uses a unique internal language it developed during training. All the languages it knows go through this internal language / neural pattern.

From what I recall reading, Google has people researching this internal language to see if they can discover any new interesting things about human thought.

https://techcrunch.com/2016/11/22/googles-ai-translation-too...

[ Parent | on HN ]
Re:Transitioning entirely to neural machine translation by dmcy22 on Thursday August 03, 2017 @05:55PM (#14924292)
Interesting, thanks for sharing!
[ Parent | on HN ]
Re:Transitioning entirely to neural machine translation by etiam on Friday August 04, 2017 @06:38AM (#14927668)
Isn't that what they are doing?

My impression of the pure DL approaches is that the preferred way to go about it is to map from each available language example, via a common latent representation, to every other available language example. The common currency is not English but a vector space representing something much more akin to the meaning underlying the statements.

[ Parent | on HN ]
Re:Transitioning entirely to neural machine translation by landon32 on Thursday August 03, 2017 @08:17PM (#14925290)
I don't know Facebook's specifics, but typically in research they will train a wide variety of examples, e.g.

English -> French French -> English English -> German French -> German

[ Parent | on HN ]