Simple tutorial for translation experts req'd


(srush) #1

This tweet makes me sad. We should fix at some point.


(Vincent Nguyen) #2

I really don’t see how this kind of toolkit could actually be used by a translator directly.

Most of them 1) won’t be Linux savvy enough 2) won’t have the GPU to train a model.

There are 2 directions I think:

  • sdl studio integration as discussed in the other thread

  • create kind of “script recipes” where you can easily see all the necessary steps from
    getting the corpus, pre-procesing, training, evaluating, spitting the bleu scores.

These “recipes” could make it easier for “openNMT newbies” to step in the project and replicates some results.

@srush if you’re familiar with Kaldi, this is the kind of “recipes” I have in mind.

Cheers.
Vincent


(srush) #3

This is very helpful. I am pretty out of touch with this community, but I would like to keep these ideas on our road map so we don’t lose touch.