News for hackers. Stuff that matters.

A comment on Unsupervised Machine Translation Using Monolingual Corpora Only [pdf]. Parent comment

Re:Unsupervised Machine Translation Using Monolingual Corpor... by DonaldPShimoda on Thursday November 02, 2017 @01:26PM (#15612364)
Most audio translation is first transcribed to a text representation, I think, and then that text is what's translated. If you assume a perfect speech recognizer (for the sake of argument), then the end translation should be the same.

Or am I misunderstanding your point?

[ Parent | on HN ]
Re:Unsupervised Machine Translation Using Monolingual Corpor... by zardo on Thursday November 02, 2017 @03:44PM (#15613590)
>Or am I misunderstanding your point?

Only that you are talking about specifics, while I was talking in generality. (IMO) unsupervised learning of semantic relationships is a 'big deal'. This seems to be a very general method that would extend to any pair of data streams, but that hasn't been proven out yet.

[ Parent | on HN ]