Transitioning entirely to neural machine translation

Re:Transitioning entirely to neural machine translation by tmsldd on Thursday August 03, 2017 @06:20PM (#14924467)

using google translation to German gives "meine Cousine und ihre Frau".. as you cited it might work just because English/German are close languages.. But, yeah, DL is just a fancy (and incomplete) mapping.

[ Parent | on HN ]

Re:Transitioning entirely to neural machine translation by justicezyx on Thursday August 03, 2017 @06:59PM (#14924756)

Is there anything isn't fancy mapping?

Use that term to down play the effectiveness of the approach seems quite surprising. Consider human needs years of study to do the same thing, which usually also makes mistakes.

Even for the example, without much analysis, it's very easy to miss the part.

[ Parent | on HN ]

Re:Transitioning entirely to neural machine translation by tmsldd on Thursday August 03, 2017 @08:20PM (#14925313)

Don't get me wrong... but If it makes you feel better, I use DL for most of my research / projects. Well, after 7 years dealing with DL I couldn't really find a better single word to describe it.

[ Parent | on HN ]

Re:Transitioning entirely to neural machine translation by visarga on Friday August 04, 2017 @03:40AM (#14927039)

How's "Fancy context dependent matching"? More dignified, right /s

In this case the context dependence part wasn't up to par, so it was just fancy mapping.

[ Parent | on HN ]