New NMT Tutorial from Graham


(srush) #1

Graham Neubig has a new tutorial that is likely of interest for those learning about NMT.

Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
https://arxiv.org/abs/1703.01619


(Karthik Ganesan) #2

Hi, Thank you for posting this! For an absolute beginner to both ML and NLP like me this is a great resource! I’ve already read through the entire thing and it really helped clear up things for me. If you happen to come across more things like this, please do share them. It is very much appreciated! :smiley:


(Etienne Monneret) #3

Yesterday, I found this nice tutorial, from the same author, clearly explaining step by step each element of a NMT:


Certainly also a must-read !
:slight_smile:


(Karthik Ganesan) #4

Thank you, @Etienne38 ! Looks great!

The only issue is everything is meant for DyNET! And as a learner, I’m already overwhelmed by the number of frameworks! Tensorflow, Theano, Torch now OpenNMT, DyNet! So far OpenNMT seems like the best bet so i might stick to that. Because I’m only interested in the inference part of NMT and speeding that up.


(srush) #5

This is great. We need something similar for this adapted to opennmt.


(Etienne Monneret) #6

@KarthikGanesan88, of course the practical part is not ONMT, but you don’t need this practical part of the tutorial to get all explanations very useful for a general understanding of NMT !