Re:The Shallowness of Google Translate
by YeGoblynQueenne on Saturday February 03, 2018 @07:46PM
(#16300585)
Yes, I know about GT's "interlingua". I've chosen my "swallow" example specifically to show that it's basically just a model of English.
Which makes a lot of sense when you realise that all the languages in the language pairs that GT's interlingua covers will have many, many more texts going to and from English, than to and from any other language. Attempting to derive a many-to-many language model from an English-dominated corpus is very likely to lead to an intermediary model that is basically English-to-many.
In fact, if you read the relevant paper [1] the dominance of English in tables etc jumps out at you.
And if you look at how Google figured out its Neural Machine Translation system has created an interlingua, that is ... visualisation. So it's not like they have some kind of principled way to demonstrate that this interlingua they advertise actually exists. They just look at some pretty images and interpret them to say that it does.
Even this visual "evidence" as they call it, is from a many-to-many language model trained on Japanese, Korean and -you guessed it- English.
Which makes a lot of sense when you realise that all the languages in the language pairs that GT's interlingua covers will have many, many more texts going to and from English, than to and from any other language. Attempting to derive a many-to-many language model from an English-dominated corpus is very likely to lead to an intermediary model that is basically English-to-many.
In fact, if you read the relevant paper [1] the dominance of English in tables etc jumps out at you.
And if you look at how Google figured out its Neural Machine Translation system has created an interlingua, that is ... visualisation. So it's not like they have some kind of principled way to demonstrate that this interlingua they advertise actually exists. They just look at some pretty images and interpret them to say that it does.
Even this visual "evidence" as they call it, is from a many-to-many language model trained on Japanese, Korean and -you guessed it- English.
__________________
[1] https://arxiv.org/pdf/1611.04558v1.pdf