Transitioning entirely to neural machine translation

Re:Transitioning entirely to neural machine translation by Retric on Thursday August 03, 2017 @02:01PM (#14922038)

45 languages * 44 other langues ~= 2000 translation directions. There are ~4,500 languages with more than 1,000 speakers ~4,500 * 4,499 ~= 20,254,500 language pairs so that's a very long way from every language.

[ Parent | on HN ]

Re:Transitioning entirely to neural machine translation by hood_syntax on Thursday August 03, 2017 @02:25PM (#14922277)

Frankly though, I imagine the vast majority of those languages are unappealing targets in terms of return on investment.

[ Parent | on HN ]

Re:Transitioning entirely to neural machine translation by flamedoge on Friday August 04, 2017 @03:28AM (#14927001)

and much smaller training data..

[ Parent | on HN ]

Re:Transitioning entirely to neural machine translation by actuator on Thursday August 03, 2017 @03:24PM (#14922895)

I guess they really don't need to cover all of them though as most of the people speaking a language with low number of speakers would be able to converse in other mainstream languages as well. I can speak four languages but I rarely converse in two of them as speakers of the two languages are usually comfortable with a mainstream language as well.

[ Parent | on HN ]

Re:Transitioning entirely to neural machine translation by rjeli on Friday August 04, 2017 @03:43AM (#14927054)

The most obvious thing to me is to use an intermediate language - I assume this has already been discussed extensively, anyone have references?

edit: I should have scrolled down https://techcrunch.com/2016/11/22/googles-ai-translation-too...

[ Parent | on HN ]

Re:Transitioning entirely to neural machine translation by jacquesm on Thursday August 03, 2017 @08:53PM (#14925478)

Even Swedish is barely in the top 100 with 8.7 million speakers.

[ Parent | on HN ]